llm - 2024_12
Navigation
Papers
Open-source Large Language models (OsLLMs) propel the democratization of natural language research by giving the flexibility to augment or update model parameters for performance improvement. Nevertheless, like proprietary LLMs, Os-LLMs offer poorer performance on low-resource languages (LRLs) than high-resource languages (HRLs), owing to smaller amounts of training data and underrepresented vocabulary. On the other hand, continual pre-training (CPT) with large amounts of language-specific data is a costly proposition in terms of data acquisition and computational resources. Our goal is to drastically reduce CPT cost. To that end, we first develop a new algorithm to select a subset of texts from a larger corpus. We show the effectiveness of our technique using very little CPT data. In search of further improvement, we design a new algorithm to select tokens to include in the LLM vocabulary. We experiment with the recent Llama-3 model and nine Indian languages with diverse scripts and extent of resource availability. For evaluation, we use IndicGenBench, a generation task benchmark dataset for Indic languages. We experiment with various CPT corpora and augmented vocabulary size and offer insights across language families.
A rapidly developing application of LLMs in XAI is to convert quantitative explanations such as SHAP into user-friendly narratives to explain the decisions made by smaller prediction models. Evaluating the narratives without relying on human preference studies or surveys is becoming increasingly important in this field. In this work we propose a framework and explore several automated metrics to evaluate LLM-generated narratives for explanations of tabular classification tasks. We apply our approach to compare several state-of-the-art LLMs across different datasets and prompt types. As a demonstration of their utility, these metrics allow us to identify new challenges related to LLM hallucinations for XAI narratives.
Large language models (LLMs) have demonstrated remarkable potential with code generation/completion tasks for hardware design. In fact, LLM-based hardware description language (HDL) code generation has enabled the industry to realize complex designs more quickly, reducing the time and effort required in the development cycle. However, the increased reliance on such automation introduces critical security risks. Notably, given that LLMs have to be trained on vast datasets of codes that are typically sourced from publicly available repositories (often without thorough validation), LLMs are susceptible to so-called data poisoning or backdoor attacks. Here, attackers inject malicious code for the training data, which can be carried over into the HDL code generated by LLMs. This threat vector can compromise the security and integrity of entire hardware systems. In this work, we propose RTL-Breaker, a novel backdoor attack framework on LLM-based HDL code generation. RTL-Breaker provides an in-depth analysis for essential aspects of this novel problem: 1) various trigger mechanisms versus their effectiveness for inserting malicious modifications, and 2) side-effects by backdoor attacks on code generation in general, i.e., impact on code quality. RTL-Breaker emphasizes the urgent need for more robust measures to safeguard against such attacks. Toward that end, we open-source our framework and all data.
Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied. To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection. Our framework employs a well-designed two-stage attack strategy. Firstly, it injects malicious tools to collect user queries, then dynamically updates the injected tools based on the stolen information to enhance subsequent attacks. These stages enable ToolCommander to execute privacy theft, launch denial-of-service attacks, and even manipulate business competition by triggering unscheduled tool-calling. Notably, the ASR reaches 91.67% for privacy theft and hits 100% for denial-of-service and unscheduled tool calling in certain cases. Our work demonstrates that these vulnerabilities can lead to severe consequences beyond simple misuse of tool-calling systems, underscoring the urgent need for robust defensive strategies to secure LLM Tool-calling systems.
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data. Meanwhile, current preference optimization research mainly targets single-question scenarios with two replies, neglecting optimization with multiple replies, which leads to a waste of data in the application. This study introduces the MPPO algorithm, which leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data. Through a comparison of Point-wise, Pair-wise, and List-wise implementations, we found that the Pair-wise approach achieves the best performance, significantly enhancing the quality of model responses. Experimental results demonstrate MPPO's outstanding performance across various benchmarks. On MT-Bench, MPPO outperforms DPO, ORPO, and SimPO. Notably, on Arena-Hard, MPPO surpasses DPO and ORPO by substantial margins. These achievements underscore the remarkable advantages of MPPO in preference optimization tasks.
The capacity of LLMs to carry out automated qualitative analysis has been questioned by corpus linguists, and it has been argued that corpus-based discourse analysis incorporating LLMs is hindered by issues of unsatisfying performance, hallucination, and irreproducibility. Our proposed method, TACOMORE, aims to address these concerns by serving as an effective prompting framework in this domain. The framework consists of four principles, i.e., Task, Context, Model and Reproducibility, and specifies five fundamental elements of a good prompt, i.e., Role Description, Task Definition, Task Procedures, Contextual Information and Output Format. We conduct experiments on three LLMs, i.e., GPT-4o, Gemini-1.5-Pro and Gemini-1.5.Flash, and find that TACOMORE helps improve LLM performance in three representative discourse analysis tasks, i.e., the analysis of keywords, collocates and concordances, based on an open corpus of COVID-19 research articles. Our findings show the efficacy of the proposed prompting framework TACOMORE in corpus-based discourse analysis in terms of Accuracy, Ethicality, Reasoning, and Reproducibility, and provide novel insights into the application and evaluation of LLMs in automated qualitative studies.
Graphs are ubiquitous data structures found in numerous real-world applications, such as drug discovery, recommender systems, and social network analysis. Graph neural networks (GNNs) have become a popular tool to learn node embeddings through message passing on these structures. However, a significant challenge arises when applying GNNs to multiple graphs with different feature spaces, as existing GNN architectures are not designed for cross-graph feature alignment. To address this, recent approaches introduce text-attributed graphs, where each node is associated with a textual description, enabling the use of a shared textual encoder to project nodes from different graphs into a unified feature space. While promising, this method relies heavily on the availability of text-attributed data, which can be difficult to obtain in practice. To bridge this gap, we propose a novel method named Topology-Aware Node description Synthesis (TANS), which leverages large language models (LLMs) to automatically convert existing graphs into text-attributed graphs. The key idea is to integrate topological information with each node's properties, enhancing the LLMs' ability to explain how graph topology influences node semantics. We evaluate our TANS on text-rich, text-limited, and text-free graphs, demonstrating that it enables a single GNN to operate across diverse graphs. Notably, on text-free graphs, our method significantly outperforms existing approaches that manually design node features, showcasing the potential of LLMs for preprocessing graph-structured data, even in the absence of textual information. The code and data are available at https://github.com/Zehong-Wang/TANS.
The ability to execute the test suite of a project is essential in many scenarios, e.g., to assess code quality and code coverage, to validate code changes made by developers or automated tools, and to ensure compatibility with dependencies. Despite its importance, executing the test suite of a project can be challenging in practice because different projects use different programming languages, software ecosystems, build systems, testing frameworks, and other tools. These challenges make it difficult to create a reliable, universal test execution method that works across different projects. This paper presents ExecutionAgent, an automated technique that installs arbitrary projects, configures them to run test cases, and produces project-specific scripts to reproduce the setup. Inspired by the way a human developer would address this task, our approach is a large language model-based agent that autonomously executes commands and interacts with the host system. The agent uses meta-prompting to gather guidelines on the latest technologies related to the given project, and it iteratively refines its process based on feedback from the previous steps. Our evaluation applies ExecutionAgent to 50 open-source projects that use 14 different programming languages and many different build and testing tools. The approach successfully executes the test suites of 33/55 projects, while matching the test results of ground truth test suite executions with a deviation of only 7.5\%. These results improve over the best previously available technique by 6.6x. The costs imposed by the approach are reasonable, with an execution time of 74 minutes and LLM costs of 0.16 dollars, on average per project. We envision ExecutionAgent to serve as a valuable tool for developers, automated programming tools, and researchers that need to execute tests across a wide variety of projects.
Large Language Model (LLM)-Powered Conversational Agents have the potential to provide users with scaled behavioral healthcare support, and potentially even deliver full-scale "AI therapy'" in the future. While such agents can already conduct fluent and proactive emotional support conversations, they inherently lack the ability to (a) consistently and reliably act by predefined rules to align their conversation with an overarching therapeutic concept and (b) make their decision paths inspectable for risk management and clinical evaluation -- both essential requirements for an "AI Therapist". In this work, we introduce a novel paradigm for dialog policy planning in conversational agents enabling them to (a) act according to an expert-written "script" that outlines the therapeutic approach and (b) explicitly transition through a finite set of states over the course of the conversation. The script acts as a deterministic component, constraining the LLM's behavior in desirable ways and establishing a basic architecture for an AI Therapist. We implement two variants of Script-Based Dialog Policy Planning using different prompting techniques and synthesize a total of 100 conversations with LLM-simulated patients. The results demonstrate the feasibility of this new technology and provide insights into the efficiency and effectiveness of different implementation variants.
Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance. However, there is growing concern that LLMs may ``game" these benchmarks due to data leakage, achieving high scores while struggling with tasks simple for humans. To substantively address the problem, we create GAOKAO-Eval, a comprehensive benchmark based on China's National College Entrance Examination (Gaokao), and conduct ``closed-book" evaluations for representative models released prior to Gaokao. Contrary to prevailing consensus, even after addressing data leakage and comprehensiveness, GAOKAO-Eval reveals that high scores still fail to truly reflect human-aligned capabilities. To better understand this mismatch, We introduce the Rasch model from cognitive psychology to analyze LLM scoring patterns and identify two key discrepancies: 1) anomalous consistent performance across various question difficulties, and 2) high variance in performance on questions of similar difficulty. In addition, We identified inconsistent grading of LLM-generated answers among teachers and recurring mistake patterns. we find that the phenomenons are well-grounded in the motivations behind OpenAI o1, and o1's reasoning-as-difficulties can mitigate the mismatch. These results show that GAOKAO-Eval can reveal limitations in LLM capabilities not captured by current benchmarks and highlight the need for more LLM-aligned difficulty analysis.
In this paper, we explore the idea of training large language models (LLMs) over highly compressed text. While standard subword tokenizers compress text by a small factor, neural text compressors can achieve much higher rates of compression. If it were possible to train LLMs directly over neurally compressed text, this would confer advantages in training and serving efficiency, as well as easier handling of long text spans. The main obstacle to this goal is that strong compression tends to produce opaque outputs that are not well-suited for learning. In particular, we find that text na\"ively compressed via Arithmetic Coding is not readily learnable by LLMs. To overcome this, we propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. Using this method, we demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks. While our method delivers worse perplexity than subword tokenizers for models trained with the same parameter count, it has the benefit of shorter sequence lengths. Shorter sequence lengths require fewer autoregressive generation steps, and reduce latency. Finally, we provide extensive analysis of the properties that contribute to learnability, and offer concrete suggestions for how to further improve the performance of high-compression tokenizers.
Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps. However, accurately localizing timestamps in videos remains challenging for Video LLMs when relying solely on temporal token prediction. Our proposed TimeRefine addresses this challenge in two ways. First, instead of directly predicting the start and end timestamps, we reformulate the temporal grounding task as a temporal refining task: the model first makes rough predictions and then refines them by predicting offsets to the target segment. This refining process is repeated multiple times, through which the model progressively self-improves its temporal localization accuracy. Second, to enhance the model's temporal perception capabilities, we incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth, thus encouraging the model to make closer and more accurate predictions. Our plug-and-play method can be integrated into most LLM-based temporal grounding approaches. The experimental results demonstrate that TimeRefine achieves 3.6% and 5.0% mIoU improvements on the ActivityNet and Charades-STA datasets, respectively. Code and pretrained models will be released.
The standard practice for developing contemporary MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. In this work, we posit an overlooked opportunity to optimize the intermediate LLM representations through a vision perspective (objective), i.e., solely natural language supervision is sub-optimal for the MLLM's visual understanding ability. To that end, we propose OLA-VLM, the first approach distilling knowledge into the LLM's hidden representations from a set of target visual representations. Firstly, we formulate the objective during the pretraining stage in MLLMs as a coupled optimization of predictive visual embedding and next text-token prediction. Secondly, we investigate MLLMs trained solely with natural language supervision and identify a positive correlation between the quality of visual representations within these models and their downstream performance. Moreover, upon probing our OLA-VLM, we observe improved representation quality owing to the embedding optimization. Thirdly, we demonstrate that our OLA-VLM outperforms the single and multi-encoder baselines, proving our approach's superiority over explicitly feeding the corresponding features to the LLM. Particularly, OLA-VLM boosts performance by an average margin of up to 2.5% on various benchmarks, with a notable improvement of 8.7% on the Depth task in CV-Bench. Our code is open-sourced at https://github.com/SHI-Labs/OLA-VLM .
Quantifying the uncertainty in the factual parametric knowledge of Large Language Models (LLMs), especially in a black-box setting, poses a significant challenge. Existing methods, which gauge a model's uncertainty through evaluating self-consistency in responses to the original query, do not always capture true uncertainty. Models might respond consistently to the origin query with a wrong answer, yet respond correctly to varied questions from different perspectives about the same query, and vice versa. In this paper, we propose a novel method, DiverseAgentEntropy, for evaluating a model's uncertainty using multi-agent interaction under the assumption that if a model is certain, it should consistently recall the answer to the original query across a diverse collection of questions about the same original query. We further implement an abstention policy to withhold responses when uncertainty is high. Our method offers a more accurate prediction of the model's reliability and further detects hallucinations, outperforming other self-consistency-based methods. Additionally, it demonstrates that existing models often fail to consistently retrieve the correct answer to the same query under diverse varied questions even when knowing the correct answer.
Given the rapid progress of generative AI, there is a pressing need to systematically compare and choose between the numerous models and configurations available. The scale and versatility of such evaluations make the use of LLM-based judges a compelling solution for this challenge. Crucially, this approach requires first to validate the quality of the LLM judge itself. Previous work has focused on instance-based assessment of LLM judges, where a judge is evaluated over a set of responses, or response pairs, while being agnostic to their source systems. We argue that this setting overlooks critical factors affecting system-level ranking, such as a judge's positive or negative bias towards certain systems. To address this gap, we conduct the first large-scale study of LLM judges as system rankers. System scores are generated by aggregating judgment scores over multiple system outputs, and the judge's quality is assessed by comparing the resulting system ranking to a human-based ranking. Beyond overall judge assessment, our analysis provides a fine-grained characterization of judge behavior, including their decisiveness and bias.
Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lead to undesirable actions. This prompts the question: Can models execute harmful behavior via inconspicuous latent states? Here, we study such obfuscated activations. We show that state-of-the-art latent-space defenses -- including sparse autoencoders, representation probing, and latent OOD detection -- are all vulnerable to obfuscated activations. For example, against probes trained to classify harmfulness, our attacks can often reduce recall from 100% to 0% while retaining a 90% jailbreaking rate. However, obfuscation has limits: we find that on a complex task (writing SQL code), obfuscation reduces model performance. Together, our results demonstrate that neural activations are highly malleable: we can reshape activation patterns in a variety of ways, often while preserving a network's behavior. This poses a fundamental challenge to latent-space defenses.
In this work, we provide a systematic analysis of how large language models (LLMs) contribute to solving planning problems. In particular, we examine how LLMs perform when they are used as problem solver, solution verifier, and heuristic guidance to improve intermediate solutions. Our analysis reveals that although it is difficult for LLMs to generate correct plans out-of-the-box, LLMs are much better at providing feedback signals to intermediate/incomplete solutions in the form of comparative heuristic functions. This evaluation framework provides insights into how future work may design better LLM-based tree-search algorithms to solve diverse planning and reasoning problems. We also propose a novel benchmark to evaluate LLM's ability to learn user preferences on the fly, which has wide applications in practical settings.
In this paper, we investigate whether current state-of-the-art large language models (LLMs) are effective as AI tutors and whether they demonstrate pedagogical abilities necessary for good AI tutoring in educational dialogues. Previous efforts towards evaluation have been limited to subjective protocols and benchmarks. To bridge this gap, we propose a unified evaluation taxonomy with eight pedagogical dimensions based on key learning sciences principles, which is designed to assess the pedagogical value of LLM-powered AI tutor responses grounded in student mistakes or confusion in the mathematical domain. We release MRBench -- a new evaluation benchmark containing 192 conversations and 1,596 responses from seven state-of-the-art LLM-based and human tutors, providing gold annotations for eight pedagogical dimensions. We assess reliability of the popular Prometheus2 LLM as an evaluator and analyze each tutor's pedagogical abilities, highlighting which LLMs are good tutors and which ones are more suitable as question-answering systems. We believe that the presented taxonomy, benchmark, and human-annotated labels will streamline the evaluation process and help track the progress in AI tutors' development.
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP). We evaluate our approach on two benchmark datasets: StepGame and SparQA, implementing three distinct strategies: (1) direct prompting baseline, (2) Facts+Rules prompting, and (3) DSPy-based LLM+ASP pipeline with iterative refinement. Our experimental results demonstrate that the LLM+ASP pipeline significantly outperforms baseline methods, achieving an average 82% accuracy on StepGame and 69% on SparQA, marking improvements of 40-50% and 8-15% respectively over direct prompting. The success stems from three key innovations: (1) effective separation of semantic parsing and logical reasoning through a modular pipeline, (2) iterative feedback mechanism between LLMs and ASP solvers that improves program rate, and (3) robust error handling that addresses parsing, grounding, and solving failures. Additionally, we propose Facts+Rules as a lightweight alternative that achieves comparable performance on complex SparQA dataset, while reducing computational overhead.Our analysis across different LLM architectures (Deepseek, Llama3-70B, GPT-4.0 mini) demonstrates the framework's generalizability and provides insights into the trade-offs between implementation complexity and reasoning capability, contributing to the development of more interpretable and reliable AI systems.
We tasked 16 state-of-the-art large language models (LLMs) with estimating the likelihood of Artificial General Intelligence (AGI) emerging by 2030. To assess the quality of these forecasts, we implemented an automated peer review process (LLM-PR). The LLMs' estimates varied widely, ranging from 3% (Reka- Core) to 47.6% (GPT-4o), with a median of 12.5%. These estimates closely align with a recent expert survey that projected a 10% likelihood of AGI by 2027, underscoring the relevance of LLMs in forecasting complex, speculative scenarios. The LLM-PR process demonstrated strong reliability, evidenced by a high Intraclass Correlation Coefficient (ICC = 0.79), reflecting notable consistency in scoring across the models. Among the models, Pplx-70b-online emerged as the top performer, while Gemini-1.5-pro-api ranked the lowest. A cross-comparison with external benchmarks, such as LMSYS Chatbot Arena, revealed that LLM rankings remained consistent across different evaluation methods, suggesting that existing benchmarks may not encapsulate some of the skills relevant for AGI prediction. We further explored the use of weighting schemes based on external benchmarks, optimizing the alignment of LLMs' predictions with human expert forecasts. This analysis led to the development of a new, 'AGI benchmark' designed to highlight performance differences in AGI-related tasks. Our findings offer insights into LLMs' capabilities in speculative, interdisciplinary forecasting tasks and emphasize the growing need for innovative evaluation frameworks for assessing AI performance in complex, uncertain real-world scenarios.
Large language models (LLMs) have recently shown significant potential in various biological tasks such as protein engineering and molecule design. These tasks typically involve black-box discrete sequence optimization, where the challenge lies in generating sequences that are not only biologically feasible but also adhere to hard fine-grained constraints. However, LLMs often struggle with such constraints, especially in biological contexts where verifying candidate solutions is costly and time-consuming. In this study, we explore the possibility of employing LLMs as highly-constrained bilevel optimizers through a methodology we refer to as Language Model Optimization with Margin Expectation (LLOME). This approach combines both offline and online optimization, utilizing limited oracle evaluations to iteratively enhance the sequences generated by the LLM. We additionally propose a novel training objective -- Margin-Aligned Expectation (MargE) -- that trains the LLM to smoothly interpolate between the reward and reference distributions. Lastly, we introduce a synthetic test suite that bears strong geometric similarity to real biophysical problems and enables rapid evaluation of LLM optimizers without time-consuming lab validation. Our findings reveal that, in comparison to genetic algorithm baselines, LLMs achieve significantly lower regret solutions while requiring fewer test function evaluations. However, we also observe that LLMs exhibit moderate miscalibration, are susceptible to generator collapse, and have difficulty finding the optimal solution when no explicit ground truth rewards are available.
Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices. Post-training quantization (PTQ) has emerged as a star approach to achieve this ambition, with best methods compressing weights to less than 2 bit on average. In this paper, we propose Channel-Relaxed Vector Quantization (CRVQ), a novel technique that significantly improves the performance of PTQ baselines at the cost of only minimal additional bits. This state-of-the-art extreme compression method achieves its results through two key innovations: (1) carefully selecting and reordering a very small subset of critical weight channels, and (2) leveraging multiple codebooks to relax the constraint of critical channels. With our method, we demonstrate a 38.9% improvement over the current strongest sub-2-bit PTQ baseline, enabling nearer lossless 1-bit compression. Furthermore, our approach offers flexible customization of quantization bit-width and performance, providing a wider range of deployment options for diverse hardware platforms.
Traditional evaluation metrics like BLEU and ROUGE fall short when capturing the nuanced qualities of generated text, particularly when there is no single ground truth. In this paper, we explore the potential of Large Language Models (LLMs), specifically Google Gemini 1, to serve as automatic evaluators for non-standardized metrics in summarization and dialog-based tasks. We conduct experiments across multiple prompting strategies to examine how LLMs fare as quality evaluators when compared with human judgments on the SummEval and USR datasets, asking the model to generate both a score as well as a justification for the score. Furthermore, we explore the robustness of the LLM evaluator by using perturbed inputs. Our findings suggest that while LLMs show promise, their alignment with human evaluators is limited, they are not robust against perturbations and significant improvements are required for their standalone use as reliable evaluators for subjective metrics.
Resource leaks, caused by resources not being released after acquisition, often lead to performance issues and system crashes. Existing static detection techniques rely on mechanical matching of predefined resource acquisition/release APIs and null-checking conditions to find unreleased resources, suffering from both (1) false negatives caused by the incompleteness of predefined resource acquisition/release APIs and (2) false positives caused by the incompleteness of resource reachability validation identification. To overcome these challenges, we propose InferROI, a novel approach that leverages the exceptional code comprehension capability of large language models (LLMs) to directly infer resource-oriented intentions (acquisition, release, and reachability validation) in code. InferROI first prompts the LLM to infer involved intentions for a given code snippet, and then incorporates a two-stage static analysis approach to check control-flow paths for resource leak detection based on the inferred intentions. We evaluate the effectiveness of InferROI in both resource-oriented intention inference and resource leak detection. Experimental results on the DroidLeaks and JLeaks datasets demonstrate InferROI achieves promising bug detection rate (59.3% and 62.5%) and false alarm rate (18.6% and 19.5%). Compared to three industrial static detectors, InferROI detects 14~45 and 149~485 more bugs in DroidLeaks and JLeaks, respectively. When applied to real-world open-source projects, InferROI identifies 29 unknown resource leak bugs (verified by authors), with 7 of them being confirmed by developers. In addition, the results of an ablation study underscores the importance of combining LLM-based inference with static analysis.
Chain-of-thought emerges as a promising technique for eliciting reasoning capabilities from Large Language Models (LLMs). However, it does not always improve task performance or accurately represent reasoning processes, leaving unresolved questions about its usage. In this paper, we diagnose the underlying mechanism by comparing the reasoning process of LLMs with humans, using causal analysis to understand the relationships between the problem instruction, reasoning, and the answer in LLMs. Our empirical study reveals that LLMs often deviate from the ideal causal chain, resulting in spurious correlations and potential consistency errors (inconsistent reasoning and answers). We also examine various factors influencing the causal structure, finding that in-context learning with examples strengthens it, while post-training techniques like supervised fine-tuning and reinforcement learning on human feedback weaken it. To our surprise, the causal structure cannot be strengthened by enlarging the model size only, urging research on new techniques. We hope that this preliminary study will shed light on understanding and improving the reasoning process in LLM.
Recently, radiance field rendering, such as 3D Gaussian Splatting (3DGS), has shown immense potential in VR content creation due to its high-quality rendering and efficient production process. However, existing physics-based interaction systems for 3DGS can only perform simple and non-realistic simulations or demand extensive user input for complex scenes, primarily due to the absence of scene understanding. In this paper, we propose LIVE-GS, a highly realistic interactive VR system powered by LLM. After object-aware GS reconstruction, we prompt GPT-4o to analyze the physical properties of objects in the scene, which are used to guide physical simulations consistent with real phenomena. We also design a GPT-assisted GS inpainting module to fill the unseen area covered by manipulative objects. To perform a precise segmentation of Gaussian kernels, we propose a feature-mask segmentation strategy. To enable rich interaction, we further propose a computationally efficient physical simulation framework through an PBD-based unified interpolation method, supporting various physical forms such as rigid body, soft body, and granular materials. Our experimental results show that with the help of LLM's understanding and enhancement of scenes, our VR system can support complex and realistic interactions without additional manual design and annotation.
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e., sensitivity to design settings such as example selection, order, and prompt formatting. Previous studies have addressed LLM bias through external adjustment of model outputs, but the internal mechanisms that lead to such bias remain unexplored. Our work delves into these mechanisms, particularly investigating how feedforward neural networks (FFNs) and attention heads result in the bias of LLMs. By Interpreting the contribution of individual FFN vectors and attention heads, we identify the biased LLM components that skew LLMs' prediction toward specific labels. To mitigate these biases, we introduce UniBias, an inference-only method that effectively identifies and eliminates biased FFN vectors and attention heads. Extensive experiments across 12 NLP datasets demonstrate that UniBias significantly enhances ICL performance and alleviates prompt brittleness of LLMs.
Large Language Models (LLMs) have shown remarkable abilities across various language tasks, but solving complex reasoning problems remains a challenge. While existing methods like Chain-of-Thought (CoT) and Tree-of-Thought (ToT) enhance reasoning by decomposing problems or structuring prompts, they typically perform a single pass of reasoning and may fail to revisit flawed paths, compromising accuracy. To address this, we propose a novel reasoning framework called Forest-of-Thought (FoT), which integrates multiple reasoning trees to leverage collective decision-making for solving complex logical problems. FoT utilizes sparse activation strategies to select the most relevant reasoning paths, improving both efficiency and accuracy. Additionally, we introduce a dynamic self-correction strategy that enables real-time error correction and learning from past mistakes, as well as consensus-guided decision making strategies to optimize correctness and computational resources. Experimental results demonstrate that the FoT framework, combined with these strategies, significantly enhances the reasoning capabilities of LLMs, enabling them to solve complex tasks with greater precision and efficiency.
In recent years, Large Language Models (LLMs) have demonstrated remarkable proficiency in comprehending and generating natural language, with a growing prevalence in the domain of recommendation systems. However, LLMs still face a significant challenge called prompt sensitivity, which refers to that it is highly susceptible to the influence of prompt words. This inconsistency in response to minor alterations in prompt input may compromise the accuracy and resilience of recommendation models. To address this issue, this paper proposes GANPrompt, a multi-dimensional LLMs prompt diversity framework based on Generative Adversarial Networks (GANs). The framework enhances the model's adaptability and stability to diverse prompts by integrating GANs generation techniques with the deep semantic understanding capabilities of LLMs. GANPrompt first trains a generator capable of producing diverse prompts by analysing multidimensional user behavioural data. These diverse prompts are then used to train the LLMs to improve its performance in the face of unseen prompts. Furthermore, to ensure a high degree of diversity and relevance of the prompts, this study introduces a mathematical theory-based diversity constraint mechanism that optimises the generated prompts to ensure that they are not only superficially distinct, but also semantically cover a wide range of user intentions. Through extensive experiments on multiple datasets, we demonstrate the effectiveness of the proposed framework, especially in improving the adaptability and robustness of recommendation systems in complex and dynamic environments. The experimental results demonstrate that GANPrompt yields substantial enhancements in accuracy and robustness relative to existing state-of-the-art methodologies.
The discovery of customer intention from dialogue plays an important role in automated support system. However, traditional text clustering methods are poorly aligned with human perceptions due to the shift from embedding distance to semantic distance, and existing quantitative metrics for text clustering may not accurately reflect the true quality of intent clusters. In this paper, we leverage the superior language understanding capabilities of Large Language Models (LLMs) for designing better-calibrated intent clustering algorithms. We first establish the foundation by verifying the robustness of fine-tuned LLM utility in semantic coherence evaluation and cluster naming, resulting in an accuracy of 97.50% and 94.40%, respectively, when compared to the human-labeled ground truth. Then, we propose an iterative clustering algorithm that facilitates cluster-level refinement and the continuous discovery of high-quality intent clusters. Furthermore, we present several LLM-in-the-loop semi-supervised clustering techniques tailored for intent discovery from customer service dialogue. Experiments on a large-scale industrial dataset comprising 1,507 intent clusters demonstrate the effectiveness of the proposed techniques. The methods outperformed existing counterparts, achieving 6.25% improvement in quantitative metrics and 12% enhancement in application-level performance when constructing an intent classifier.
The integration of large language models (LLMs) into computing education offers many potential benefits to student learning, and several novel pedagogical approaches have been reported in the literature. However LLMs also present challenges, one of the most commonly cited being that of student over-reliance. This challenge is compounded by the fact that LLMs are always available to provide instant help and solutions to students, which can undermine their ability to independently solve problems and diagnose and resolve errors. Providing instructor oversight of LLM-generated content can mitigate this problem, however it is often not practical in real-time learning contexts. Online class discussion forums, which are widely used in computing education, present an opportunity for exploring instructor oversight because they operate asynchronously. Unlike real-time interactions, the discussion forum format aligns with the expectation that responses may take time, making oversight not only feasible but also pedagogically appropriate. In this practitioner paper, we present the design, deployment, and evaluation of a `bot' module that is controlled by the instructor, and integrated into an online discussion forum. The bot assists the instructor by generating draft responses to student questions, which are reviewed, modified, and approved before release. Key features include the ability to leverage course materials, access archived discussions, and publish responses anonymously to encourage open participation. We report our experiences using this tool in a 12-week second-year software engineering course on object-oriented programming. Instructor feedback confirmed the tool successfully alleviated workload but highlighted a need for improvement in handling complex, context-dependent queries. We report the features that were viewed as most beneficial, and suggest avenues for future exploration.
Implicit sentiment analysis (ISA) presents significant challenges due to the absence of salient cue words. Previous methods have struggled with insufficient data and limited reasoning capabilities to infer underlying opinions. Integrating multi-task learning (MTL) with large language models (LLMs) offers the potential to enable models of varying sizes to reliably perceive and recognize genuine opinions in ISA. However, existing MTL approaches are constrained by two sources of uncertainty: data-level uncertainty, arising from hallucination problems in LLM-generated contextual information, and task-level uncertainty, stemming from the varying capacities of models to process contextual information. To handle these uncertainties, we introduce MT-ISA, a novel MTL framework that enhances ISA by leveraging the generation and reasoning capabilities of LLMs through automatic MTL. Specifically, MT-ISA constructs auxiliary tasks using generative LLMs to supplement sentiment elements and incorporates automatic MTL to fully exploit auxiliary data. We introduce data-level and task-level automatic weight learning (AWL), which dynamically identifies relationships and prioritizes more reliable data and critical tasks, enabling models of varying sizes to adaptively learn fine-grained weights based on their reasoning capabilities. We investigate three strategies for data-level AWL, while also introducing homoscedastic uncertainty for task-level AWL. Extensive experiments reveal that models of varying sizes achieve an optimal balance between primary prediction and auxiliary tasks in MT-ISA. This underscores the effectiveness and adaptability of our approach.
Enabling LLMs to handle lengthy context is currently a research hotspot. Most LLMs are built upon rotary position embedding (RoPE), a popular position encoding method. Therefore, a prominent path is to extrapolate the RoPE trained on comparably short texts to far longer texts. A heavy bunch of efforts have been dedicated to boosting the extrapolation via extending the formulations of the RoPE, however, few of them have attempted to showcase their inner workings comprehensively. In this paper, we are driven to offer a straightforward yet in-depth understanding of RoPE extensions from an attention perspective and on two benchmarking tasks. A broad array of experiments reveals several valuable findings: 1) Maintaining attention patterns to those at the pretrained length improves extrapolation; 2) Large attention uncertainty leads to retrieval errors; 3) Using longer continual pretraining lengths for RoPE extensions could reduce attention uncertainty and significantly enhance extrapolation.
Context: The emergence of Large Language Models (LLMs) has significantly transformed Software Engineering (SE) by providing innovative methods for analyzing software repositories. Objectives: Our objective is to establish a practical framework for future SE researchers needing to enhance the data collection and dataset while conducting software repository mining studies using LLMs. Method: This experience report shares insights from two previous repository mining studies, focusing on the methodologies used for creating, refining, and validating prompts that enhance the output of LLMs, particularly in the context of data collection in empirical studies. Results: Our research packages a framework, coined Prompt Refinement and Insights for Mining Empirical Software repositories (PRIMES), consisting of a checklist that can improve LLM usage performance, enhance output quality, and minimize errors through iterative processes and comparisons among different LLMs. We also emphasize the significance of reproducibility by implementing mechanisms for tracking model results. Conclusion: Our findings indicate that standardizing prompt engineering and using PRIMES can enhance the reliability and reproducibility of studies utilizing LLMs. Ultimately, this work calls for further research to address challenges like hallucinations, model biases, and cost-effectiveness in integrating LLMs into workflows.
This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning. Covering three practical domains -- airline baggage fees, NBA transactions, and tax regulations -- RuleArena assesses LLMs' proficiency in handling intricate natural language instructions that demand long-context understanding, logical reasoning, and accurate mathematical computation. Two key attributes distinguish RuleArena from traditional rule-based reasoning benchmarks: (1) it extends beyond standard first-order logic representations, and (2) it is grounded in authentic, practical scenarios, providing insights into the suitability and reliability of LLMs for real-world applications. Our findings reveal several notable limitations in LLMs: (1) they struggle to identify and apply the appropriate rules, frequently becoming confused by similar but distinct regulations, (2) they cannot consistently perform accurate mathematical computations, even when they correctly identify the relevant rules, and (3) in general, they perform poorly in the benchmark. These results highlight significant challenges in advancing LLMs' rule-guided reasoning capabilities in real-life applications.
Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
Interpretability is a key challenge in fostering trust for Large Language Models (LLMs), which stems from the complexity of extracting reasoning from model's parameters. We present the Frame Representation Hypothesis, a theoretically robust framework grounded in the Linear Representation Hypothesis (LRH) to interpret and control LLMs by modeling multi-token words. Prior research explored LRH to connect LLM representations with linguistic concepts, but was limited to single token analysis. As most words are composed of several tokens, we extend LRH to multi-token words, thereby enabling usage on any textual data with thousands of concepts. To this end, we propose words can be interpreted as frames, ordered sequences of vectors that better capture token-word relationships. Then, concepts can be represented as the average of word frames sharing a common concept. We showcase these tools through Top-k Concept-Guided Decoding, which can intuitively steer text generation using concepts of choice. We verify said ideas on Llama 3.1, Gemma 2, and Phi 3 families, demonstrating gender and language biases, exposing harmful content, but also potential to remediate them, leading to safer and more transparent LLMs. Code is available at https://github.com/phvv-me/frame-representation-hypothesis.git
In recent years, Large Language Models (LLMs) like ChatGPT have seen considerable advancements and have been applied in diverse fields. Built on the Transformer architecture, these models are trained on extensive datasets, enabling them to understand and generate human language effectively. In the financial domain, the deployment of LLMs is gaining momentum. These models are being utilized for automating financial report generation, forecasting market trends, analyzing investor sentiment, and offering personalized financial advice. Leveraging their natural language processing capabilities, LLMs can distill key insights from vast financial data, aiding institutions in making informed investment choices and enhancing both operational efficiency and customer satisfaction. In this study, we provide a comprehensive overview of the emerging integration of LLMs into various financial tasks. Additionally, we conducted holistic tests on multiple financial tasks through the combination of natural language instructions. Our findings show that GPT-4 effectively follow prompt instructions across various financial tasks. This survey and evaluation of LLMs in the financial domain aim to deepen the understanding of LLMs' current role in finance for both financial practitioners and LLM researchers, identify new research and application prospects, and highlight how these technologies can be leveraged to solve practical challenges in the finance industry.
The prevalence of unhealthy eating habits has become an increasingly concerning issue in the United States. However, major food recommendation platforms (e.g., Yelp) continue to prioritize users' dietary preferences over the healthiness of their choices. Although efforts have been made to develop health-aware food recommendation systems, the personalization of such systems based on users' specific health conditions remains under-explored. In addition, few research focus on the interpretability of these systems, which hinders users from assessing the reliability of recommendations and impedes the practical deployment of these systems. In response to this gap, we first establish two large-scale personalized health-aware food recommendation benchmarks at the first attempt. We then develop a novel framework, Multi-Objective Personalized Interpretable Health-aware Food Recommendation System (MOPI-HFRS), which provides food recommendations by jointly optimizing the three objectives: user preference, personalized healthiness and nutritional diversity, along with an large language model (LLM)-enhanced reasoning module to promote healthy dietary knowledge through the interpretation of recommended results. Specifically, this holistic graph learning framework first utilizes two structure learning and a structure pooling modules to leverage both descriptive features and health data. Then it employs Pareto optimization to achieve designed multi-facet objectives. Finally, to further promote the healthy dietary knowledge and awareness, we exploit an LLM by utilizing knowledge-infusion, prompting the LLMs with knowledge obtained from the recommendation model for interpretation.
As Large Language Models (LLMs) continue to evolve, more are being designed to handle long-context inputs. Despite this advancement, most of them still face challenges in accurately handling long-context tasks, often showing the "lost in the middle" issue. We identify that insufficient retrieval capability is one of the important reasons for this issue. To tackle this challenge, we propose a novel approach to design training data for long-context tasks, aiming at augmenting LLMs' proficiency in extracting key information from long context. Specially, we incorporate an additional part named "paraphrasing the original text" when constructing the answer of training samples and then fine-tuning the model. Experimenting on LongBench and NaturalQuestions Multi-document-QA dataset with models of Llama and Qwen series, our method achieves an improvement of up to 8.48% and 4.48% in average scores, respectively, showing effectiveness in improving the model's performance on long-context tasks.
As LLMs continue to become more powerful and versatile, human evaluation has quickly become intractable at scale and reliance on automatic metrics has become the norm. Recently, it has been shown that LLMs are themselves state-of-the-art evaluators for many tasks. These Autoraters are typically designed so that they generalize to new systems and test sets. In practice, however, evaluation is performed on a small set of fixed, canonical test sets, which are carefully curated to measure certain capabilities of interest and are not changed frequently. In this work, we design a method which specializes a prompted Autorater to a given test set, by leveraging historical ratings on the test set to construct in-context learning (ICL) examples. We evaluate our Specialist method on the task of fine-grained machine translation evaluation, and show that it dramatically outperforms the state-of-the-art XCOMET metric by 54% and 119% on the WMT'23 and WMT'24 test sets, respectively. We perform extensive analyses to understand the representations learned by our Specialist metrics, and how variability in rater behavior affects their performance. We also verify the generalizability and robustness of our Specialist method for designing automatic metrics across different numbers of ICL examples, LLM backbones, systems to evaluate, and evaluation tasks.
Game-theoretic simulations are a versatile tool for exploring interactions of both natural and artificial agents. However, modelling real-world scenarios and developing simulations often require substantial human expertise and effort. To streamline this process, we present a framework that enables the autoformalization of game-theoretic scenarios using agents augmented by large language models (LLMs). In this approach, LLM-augmented agents translate natural language scenario descriptions into executable logic programs that define the rules of each game, validating these programs for syntactic accuracy. A tournament simulation is then conducted, during which the agents test the functionality of the generated games by playing them. When a ground truth payoff matrix is available, an exact semantic validation can also be performed. The validated games can then be used in further simulations to assess the effectiveness of different strategies. We evaluate our approach on a diverse set of 55 natural language descriptions across five well-known 2x2 simultaneous-move games, demonstrating 96% syntactic and 87% semantic correctness in the generated game rules. Additionally, we assess the LLM-augmented agents' capability to autoformalize strategies for gameplay.
The advent of Large Language Models (LLMs) and Artificial Intelligence (AI) tools has revolutionized various facets of our lives, particularly in the realm of social media. For students, these advancements have unlocked unprecedented opportunities for learning, collaboration, and personal growth. AI-driven applications are transforming how students interact with social media, offering personalized content and recommendations, and enabling smarter, more efficient communication. Recent studies utilizing data from UniversityCube underscore the profound impact of AI tools on students' academic and social experiences. These studies reveal that students engaging with AI-enhanced social media platforms report higher academic performance, enhanced critical thinking skills, and increased engagement in collaborative projects. Moreover, AI tools assist in filtering out distracting content, allowing students to concentrate more on educational materials and pertinent discussions. The integration of LLMs in social media has further facilitated improved peer-to-peer communication and mentorship opportunities. AI algorithms effectively match students based on shared academic interests and career goals, fostering a supportive and intellectually stimulating online community, thereby contributing to increased student satisfaction and retention rates. In this article, we delve into the data provided by UniversityCube to explore how LLMs and AI tools are specifically transforming social media for students. Through case studies and statistical analyses, we offer a comprehensive understanding of the educational and social benefits these technologies offer. Our exploration highlights the potential of AI-driven tools to create a more enriched, efficient, and supportive educational environment for students in the digital age.
There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective and then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets. Our results indicate that compared to template-based synthetic datasets, crowdsourcing approaches normally sacrifice the coverage of configurations (i.e., mood and figure) of categorical syllogisms for more language variations, thus bringing challenges to fully testing LLMs under different situations. We then proceed to summarize the findings and observations for the performances of LLMs to infer the validity of syllogisms from the current literature. The error rate breakdown analyses suggest that the interpretation of the quantifiers seems to be the current bottleneck that limits the performances of the LLMs and is thus worth more attention. Finally, we discuss several points that might be worth considering when researchers plan on the future release of categorical syllogism datasets. We hope our work will not only provide a timely review of the current literature regarding categorical syllogisms, but also motivate more interdisciplinary research between communities, specifically computational linguists and logicians.
This study investigates efficient deduplication techniques for a large NLP dataset of economic research paper titles. We explore various pairing methods alongside established distance measures (Levenshtein distance, cosine similarity) and a sBERT model for semantic evaluation. Our findings suggest a potentially low prevalence of duplicates based on the observed semantic similarity across different methods. Further exploration with a human-annotated ground truth set is completed for a more conclusive assessment. The result supports findings from the NLP, LLM based distance metrics.
Interpretability methods seek to understand language model representations, yet the outputs of most such methods -- circuits, vectors, scalars -- are not immediately human-interpretable. In response, we introduce LatentQA, the task of answering open-ended questions about model activations in natural language. Towards solving LatentQA, we propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs, similar to how visual instruction tuning trains on question-answer pairs associated with images. We use the decoder for diverse reading applications, such as extracting relational knowledge from representations or uncovering system prompts governing model behavior. Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations. Finally, we extend LatentQA to reveal harmful model capabilities, such as generating recipes for bioweapons and code for hacking.
Large Language Models (LLMs) have demonstrated great potential in various language processing tasks, and recent studies have explored their application in compiler optimizations. However, all these studies focus on the conventional open-source LLMs, such as Llama2, which lack enhanced reasoning mechanisms. In this study, we investigate the errors produced by the fine-tuned 7B-parameter Llama2 model as it attempts to learn and apply a simple peephole optimization for the AArch64 assembly code. We provide an analysis of the errors produced by the LLM and compare it with state-of-the-art OpenAI models which implement advanced reasoning logic, including GPT-4o and GPT-o1 (preview). We demonstrate that OpenAI GPT-o1, despite not being fine-tuned, outperforms the fine-tuned Llama2 and GPT-4o. Our findings indicate that this advantage is largely due to the chain-of-thought reasoning implemented in GPT-o1. We hope our work will inspire further research on using LLMs with enhanced reasoning mechanisms and chain-of-thought for code generation and optimization.
Sequential recommendation systems aim to provide personalized recommendations for users based on their interaction history. To achieve this, they often incorporate auxiliary information, such as textual descriptions of items and auxiliary tasks, like predicting user preferences and intent. Despite numerous efforts to enhance these models, they still suffer from limited personalization. To address this issue, we propose a new paradigm, which we term preference discerning. In preference dscerning, we explicitly condition a generative sequential recommendation system on user preferences within its context. To this end, we generate user preferences using Large Language Models (LLMs) based on user reviews and item-specific data. To evaluate preference discerning capabilities of sequential recommendation systems, we introduce a novel benchmark that provides a holistic evaluation across various scenarios, including preference steering and sentiment following. We assess current state-of-the-art methods using our benchmark and show that they struggle to accurately discern user preferences. Therefore, we propose a new method named Mender ($\textbf{M}$ultimodal Prefer$\textbf{en}$ce $\textbf{d}$iscern$\textbf{er}$), which improves upon existing methods and achieves state-of-the-art performance on our benchmark. Our results show that Mender can be effectively guided by human preferences even though they have not been observed during training, paving the way toward more personalized sequential recommendation systems. We will open-source the code and benchmarks upon publication.
Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.
Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from the end-user's perspective. Although ET has proven effective in system-level testing of interactive systems, the need for manual execution has hindered large-scale adoption. In this work, we explore the feasibility, challenges and road ahead of automated scenario-based ET (a.k.a soap opera testing). We conduct a formative study, identifying key insights for effective manual soap opera testing and challenges in automating the process. We then develop a multi-agent system leveraging LLMs and a Scenario Knowledge Graph (SKG) to automate soap opera testing. The system consists of three multi-modal agents, Planner, Player, and Detector that collaborate to execute tests and identify potential bugs. Experimental results demonstrate the potential of automated soap opera testing, but there remains a significant gap compared to manual execution, especially under-explored scenario boundaries and incorrectly identified bugs. Based on the observation, we envision road ahead for the future of automated soap opera testing, focusing on three key aspects: the synergy of neural and symbolic approaches, human-AI co-learning, and the integration of soap opera testing with broader software engineering practices. These insights aim to guide and inspire the future research.
Visual programming prompts LLMs (large language mod-els) to generate executable code for visual tasks like visual question answering (VQA). Prompt-based methods are difficult to improve while also being unreliable and costly in both time and money. Our goal is to develop an efficient visual programming system without 1) using prompt-based LLMs at inference time and 2) a large set of program and answer annotations. We develop a synthetic data augmentation approach and alternative program generation method based on decoupling programs into higher-level skills called templates and the corresponding arguments. Our results show that with data augmentation, prompt-free smaller LLMs ($\approx$ 1B parameters) are competitive with state-of-the art models with the added benefit of much faster inference
Large Language Models (LLMs) have revolutionized natural language processing (NLP) by delivering state-of-the-art performance across a variety of tasks. Among these, Transformer-based models like BERT and GPT rely on pooling layers to aggregate token-level embeddings into sentence-level representations. Common pooling mechanisms such as Mean, Max, and Weighted Sum play a pivotal role in this aggregation process. Despite their widespread use, the comparative performance of these strategies on different LLM architectures remains underexplored. To address this gap, this paper investigates the effects of these pooling mechanisms on two prominent LLM families -- BERT and GPT, in the context of sentence-level sentiment analysis. Comprehensive experiments reveal that each pooling mechanism exhibits unique strengths and weaknesses depending on the task's specific requirements. Our findings underline the importance of selecting pooling methods tailored to the demands of particular applications, prompting a re-evaluation of common assumptions regarding pooling operations. By offering actionable insights, this study contributes to the optimization of LLM-based models for downstream tasks.
Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world scenarios that involve diverse speaker characteristics, environmental and content factors. To address this, we introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations. Extensive experiments reveal the limitations of current LLM-based voice assistant models and offer valuable insights for future research and development in this field.
Multi-hand semantic grasp generation aims to generate feasible and semantically appropriate grasp poses for different robotic hands based on natural language instructions. Although the task is highly valuable, due to the lack of multi-hand grasp datasets with fine-grained contact description between robotic hands and objects, it is still a long-standing difficult task. In this paper, we present Multi-GraspSet, the first large-scale multi-hand grasp dataset with automatically contact annotations. Based on Multi-GraspSet, we propose Multi-GraspLLM, a unified language-guided grasp generation framework. It leverages large language models (LLM) to handle variable-length sequences, generating grasp poses for diverse robotic hands in a single unified architecture. Multi-GraspLLM first aligns the encoded point cloud features and text features into a unified semantic space. It then generates grasp bin tokens which are subsequently converted into grasp pose for each robotic hand via hand-aware linear mapping. The experimental results demonstrate that our approach significantly outperforms existing methods on Multi-GraspSet. More information can be found on our project page https://multi-graspllm.github.io.
Prompting LLMs for complex tasks (e.g., building a trip advisor chatbot) needs humans to clearly articulate customized requirements (e.g., "start the response with a tl;dr"). However, existing prompt engineering instructions often lack focused training on requirement articulation and instead tend to emphasize increasingly automatable strategies (e.g., tricks like adding role-plays and "think step-by-step"). To address the gap, we introduce Requirement-Oriented Prompt Engineering (ROPE), a paradigm that focuses human attention on generating clear, complete requirements during prompting. We implement ROPE through an assessment and training suite that provides deliberate practice with LLM-generated feedback. In a randomized controlled experiment with 30 novices, ROPE significantly outperforms conventional prompt engineering training (20% vs. 1% gains), a gap that automatic prompt optimization cannot close. Furthermore, we demonstrate a direct correlation between the quality of input requirements and LLM outputs. Our work paves the way to empower more end-users to build complex LLM applications.
Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data collection or rely on the less dependable option of using another LLM to generate corrective data. In this paper, we aim to take this problem and overcome limitations of requiring significant high-quality human data. Our method requires only a small set of unsafe responses to toxic prompts, easily obtained from the unsafe LLM itself. By employing a semantic cost combined with a negative Earth Mover Distance (EMD) loss, we guide the LLM away from generating unsafe responses. Additionally, we propose a novel lower bound for EMD loss, enabling more efficient optimization. Our results demonstrate superior performance and data efficiency compared to baselines, and we further examine the nuanced effects of over-alignment and potential degradation of language capabilities when using contrastive data.
Autonomous program improvement typically involves automatically producing bug fixes and feature additions. Such program improvement can be accomplished by a combination of large language model (LLM) and program analysis capabilities, in the form of an LLM agent. Since program repair or program improvement typically requires a specification of intended behavior - specification inference can be useful for producing high quality program patches. In this work, we examine efficient and low-cost workflows for iterative specification inference within an LLM agent. Given a GitHub issue to be resolved in a software project, our goal is to conduct iterative code search accompanied by specification inference - thereby inferring intent from both the project structure and behavior. The intent thus captured is examined by a reviewer agent with the goal of vetting the patches as well as providing a measure of confidence in the vetted patches. Our approach SpecRover (AutoCodeRover-v2) is built on the open-source LLM agent AutoCodeRover. In an evaluation on the full SWE-Bench consisting of 2294 GitHub issues, it shows more than 50% improvement in efficacy over AutoCodeRover. Compared to the open-source agents available, our work shows modest cost ($0.65 per issue) in resolving an average GitHub issue in SWE-Bench lite. The production of explanation by SpecRover allows for a better "signal" to be given to the developer, on when the suggested patches can be accepted with confidence. SpecRover also seeks to demonstrate the continued importance of specification inference in automated program repair, even as program repair technologies enter the LLM era.
Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks and have recently expanded their impact to coding tasks, bridging the gap between natural languages (NL) and programming languages (PL). This taxonomy-based survey provides a comprehensive analysis of LLMs in the NL-PL domain, investigating how these models are utilized in coding tasks and examining their methodologies, architectures, and training processes. We propose a taxonomy-based framework that categorizes relevant concepts, providing a unified classification system to facilitate a deeper understanding of this rapidly evolving field. This survey offers insights into the current state and future directions of LLMs in coding tasks, including their applications and limitations.
Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, a predictive model for self-consistency based LLM inferences, and empirically evaluate it using AutoFL, a recently proposed LLM-based fault localisation technique, as the target technique that uses self-consistency. Lachesis converts collected reasoning paths from AutoFL using specifically designed reasoning path representations, and trains LSTM and GCN models to predict whether a given set of reasoning paths would result in a correct answer. The results suggest that Lachesis can predict the correctness of answers with a precision of up to 0.8136, highlighting the possibility of training a predictive model that can allow early termination of inferences that are not likely to be successful.
The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.
Financial analysis heavily relies on the evaluation of earnings reports to gain insights into company performance. Traditional generation of these reports requires extensive financial expertise and is time-consuming. With the impressive progress in Large Language Models (LLMs), a wide variety of financially focused LLMs has emerged, addressing tasks like sentiment analysis and entity recognition in the financial domain. This paper presents a novel challenge: developing an LLM specifically for automating the generation of earnings reports analysis. Our methodology involves an in-depth analysis of existing earnings reports followed by a unique approach to fine-tune an LLM for this purpose. This approach combines retrieval augmentation and the generation of instruction-based data, specifically tailored for the financial sector, to enhance the LLM's performance. With extensive financial documents, we construct financial instruction data, enabling the refined adaptation of our LLM to financial contexts. Preliminary results indicate that our augmented LLM outperforms general open-source models and rivals commercial counterparts like GPT-3.5 in financial applications. Our research paves the way for streamlined and insightful automation in financial report generation, marking a significant stride in the field of financial analysis.
Outlier detection (OD), also known as anomaly detection, is a critical machine learning (ML) task with applications in fraud detection, network intrusion detection, clickstream analysis, recommendation systems, and social network moderation. Among open-source libraries for outlier detection, the Python Outlier Detection (PyOD) library is the most widely adopted, with over 8,500 GitHub stars, 25 million downloads, and diverse industry usage. However, PyOD currently faces three limitations: (1) insufficient coverage of modern deep learning algorithms, (2) fragmented implementations across PyTorch and TensorFlow, and (3) no automated model selection, making it hard for non-experts. To address these issues, we present PyOD Version 2 (PyOD 2), which integrates 12 state-of-the-art deep learning models into a unified PyTorch framework and introduces a large language model (LLM)-based pipeline for automated OD model selection. These improvements simplify OD workflows, provide access to 45 algorithms, and deliver robust performance on various datasets. In this paper, we demonstrate how PyOD 2 streamlines the deployment and automation of OD models and sets a new standard in both research and industry. PyOD 2 is accessible at [https://github.com/yzhao062/pyod](https://github.com/yzhao062/pyod). This study aligns with the Web Mining and Content Analysis track, addressing topics such as the robustness of Web mining methods and the quality of algorithmically-generated Web data.
The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large language models (LLMs). While LLMs excel in program synthesis, their direct application to ARC yields limited success. To address this, we introduce ConceptSearch, a novel function-search algorithm that leverages LLMs for program generation and employs a concept-based scoring method to guide the search efficiently. Unlike simplistic pixel-based metrics like Hamming distance, ConceptSearch evaluates programs on their ability to capture the underlying transformation concept reflected in the input-output examples. We explore three scoring functions: Hamming distance, a CNN-based scoring function, and an LLM-based natural language scoring function. Experimental results demonstrate the effectiveness of ConceptSearch, achieving a significant performance improvement over direct prompting with GPT-4. Moreover, our novel concept-based scoring exhibits up to 30% greater efficiency compared to Hamming distance, measured in terms of the number of iterations required to reach the correct solution. These findings highlight the potential of LLM-driven program search when integrated with concept-based guidance for tackling challenging generalization problems like ARC.
Large language models (LLMs) have been demonstrated to possess the capabilities to understand fundamental graph properties and address various graph reasoning tasks. Existing methods fine-tune LLMs to understand and execute graph reasoning tasks by specially designed task instructions. However, these Text-Instruction methods generally exhibit poor performance. Inspired by tool learning, researchers propose Tool-Instruction methods to solve various graph problems by special tool calling (e.g., function, API and model), achieving significant improvements in graph reasoning tasks. Nevertheless, current Tool-Instruction approaches focus on the tool information and ignore the graph structure information, which leads to significantly inferior performance on small-scale LLMs (less than 13B). To tackle this issue, we propose GraphTool-Instruction, an innovative Instruction-tuning approach that decomposes the graph reasoning task into three distinct subtasks (i.e., graph extraction, tool name identification and tool parameter extraction), and design specialized instructions for each subtask. Our GraphTool-Instruction can be used as a plug-and-play prompt for different LLMs without fine-tuning. Moreover, building on GraphTool-Instruction, we develop GTools, a dataset that includes twenty graph reasoning tasks, and create a graph reasoning LLM called GraphForge based on Llama3-8B. We conduct extensive experiments on twenty graph reasoning tasks with different graph types (e.g., graph size or graph direction), and we find that GraphTool-Instruction achieves SOTA compared to Text-Instruction and Tool-Instruction methods. Fine-tuned on GTools, GraphForge gets further improvement of over 30% compared to the Tool-Instruction enhanced GPT-3.5-turbo, and it performs comparably to the high-cost GPT-4o. Our codes and data are available at https://anonymous.4open.science/r/GraphTool-Instruction.
The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our investigation reveals that LLMs intrinsically reward in-language semantically aligned cross-lingual instances over direct cross-lingual semantic alignments, with a pronounced disparity in handling time-sensitive queries in the X-ICL setup. Such queries demand sound temporal reasoning ability from LLMs, yet the advancements have predominantly focused on English. This study aims to bridge this gap by improving temporal reasoning capabilities in low-resource languages. To this end, we introduce mTEMPREASON a temporal reasoning dataset aimed at the varied degrees of low-resource languages and propose Cross-Lingual Time-Sensitive Semantic Alignment (CLiTSSA), a novel method to improve temporal reasoning in these contexts. To facilitate this, we construct an extension of mTEMPREASON comprising pairs of parallel cross-language temporal queries along with their anticipated in-language semantic similarity scores. Our empirical evidence underscores the superior performance of CLiTSSA compared to established baselines across three languages - Romanian, German, and French, encompassing three temporal tasks and including a diverse set of four contemporaneous LLMs. This marks a significant step forward in addressing resource disparity in the context of temporal reasoning across languages.
Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents. The advancement of LLMs is frequently hindered by the scarcity of high-quality data, much of which is inherently sensitive. Federated learning (FL) offers a potential solution by facilitating the collaborative training of distributed LLMs while safeguarding private data. However, FL frameworks face significant bandwidth and computational demands, along with challenges from heterogeneous data distributions. The emerging in-context learning capability of LLMs offers a promising approach by aggregating natural language rather than bulky model parameters. Yet, this method risks privacy leakage, as it necessitates the collection and presentation of data samples from various clients during aggregation. In this paper, we propose a novel privacy-preserving Federated In-Context LLM Agent Learning (FICAL) algorithm, which to our best knowledge for the first work unleashes the power of in-context learning to train diverse LLM agents through FL. In our design, knowledge compendiums generated by a novel LLM-enhanced Knowledge Compendiums Generation (KCG) module are transmitted between clients and the server instead of model parameters in previous FL methods. Apart from that, an incredible Retrieval Augmented Generation (RAG) based Tool Learning and Utilizing (TLU) module is designed and we incorporate the aggregated global knowledge compendium as a teacher to teach LLM agents the usage of tools. We conducted extensive experiments and the results show that FICAL has competitive performance compared to other SOTA baselines with a significant communication cost decrease of $\mathbf{3.33\times10^5}$ times.
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diverse real-world backgrounds and the requirement for maintaining visual naturality. Building upon this challenge, we reformulate physical adversarial attacks as a one-shot patch-generation problem. Our approach generates adversarial patches through a deep generative model that considers the specific scene context, enabling direct physical deployment in matching environments. The primary challenge lies in simultaneously achieving two objectives: generating adversarial patches that effectively mislead object detection systems while determining contextually appropriate placement within the scene. We propose MAGIC (Mastering Physical Adversarial Generation In Context), a novel framework powered by multi-modal LLM agents to address these challenges. MAGIC automatically understands scene context and orchestrates adversarial patch generation through the synergistic interaction of language and vision capabilities. MAGIC orchestrates three specialized LLM agents: The adv-patch generation agent (GAgent) masters the creation of deceptive patches through strategic prompt engineering for text-to-image models. The adv-patch deployment agent (DAgent) ensures contextual coherence by determining optimal placement strategies based on scene understanding. The self-examination agent (EAgent) completes this trilogy by providing critical oversight and iterative refinement of both processes. We validate our method on both digital and physical level, \ie, nuImage and manually captured real scenes, where both statistical and visual results prove that our MAGIC is powerful and effectively for attacking wide-used object detection systems.
In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs' factuality self-assessment, and discuss its relation to the models' context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute.
Integrating inertial measurement units (IMUs) with large language models (LLMs) expands the potential of multimodal AI, enabling more nuanced human activity analysis. In this paper, we introduce LLaSA (Large Language and Sensor Assistant), a multimodal large language model built on LIMU-BERT and Llama, designed to interpret and answer queries related to human activities and motion analysis, leveraging sensor data and contextual reasoning. To develop LLaSA, we introduce two key datasets: SensorCaps, a comprehensive collection of 35,960 IMU-derived narratives with handcrafted features, and OpenSQA, an instruction-following dataset containing 179,727 question-answer pairs aware of the sensor and human activity context. These datasets provide diverse and rich inputs to train LLaSA for complex sensor-based queries. To optimize LLaSA's performance, we apply a unique hyperparameter tuning method, which significantly enhances its effectiveness in contextual question-answering tasks. Extensive evaluations, including a human-led assessment of the question-answering, demonstrate that LLaSA achieves superior data interpretation and context-aware responses compared to GPT-3.5-Turbo and Vicuna-1.5-13b-16K. These contributions advance the frontier of sensor-aware LLMs and create new opportunities for impactful multimodal research in healthcare, sports science, and human-computer interactions. Our code repository and datasets can be found at https://github.com/BASHLab/LLaSA.
This study examines whether large language models (LLMs), such as ChatGPT, specifically the latest GPT-4o-mini, exhibit sensitivity to repeated prompts and whether repeating a question can improve response accuracy. We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements of the query. To test this, we evaluate ChatGPT's performance on a large sample of two reading comprehension datasets under both open-book and closed-book settings, varying the repetition of each question to 1, 3, or 5 times per prompt. Our findings indicate that the model does not demonstrate sensitivity to repeated questions, highlighting its robustness and consistency in this context.
Recent advances in large language models (LLMs) have led to the development of artificial intelligence (AI)-powered tutoring chatbots, showing promise in providing broad access to high-quality personalized education. Existing works have studied how to make LLMs follow tutoring principles, but have not studied broader uses of LLMs for supporting tutoring. Up until now, tracing student knowledge and analyzing misconceptions has been difficult and time-consuming to implement for open-ended dialogue tutoring. In this work, we investigate whether LLMs can be supportive of this task: we first use LLM prompting methods to identify the knowledge components/skills involved in each dialogue turn, i.e., a tutor utterance posing a task or a student utterance that responds to it. We also evaluate whether the student responds correctly to the tutor and verify the LLM's accuracy using human expert annotations. We then apply a range of knowledge tracing (KT) methods on the resulting labeled data to track student knowledge levels over an entire dialogue. We conduct experiments on two tutoring dialogue datasets, and show that a novel yet simple LLM-based method, LLMKT, significantly outperforms existing KT methods in predicting student response correctness in dialogues. We perform extensive qualitative analyses to highlight the challenges in dialogueKT and outline multiple avenues for future work.
Engaging in the deliberate generation of abnormal outputs from Large Language Models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people perform such attacks, defining LLM red-teaming based on extensive and diverse evidence. Using a formal qualitative methodology, we interviewed dozens of practitioners from a broad range of backgrounds, all contributors to this novel work of attempting to cause LLMs to fail. We focused on the research questions of defining LLM red teaming, uncovering the motivations and goals for performing the activity, and characterizing the strategies people use when attacking LLMs. Based on the data, LLM red teaming is defined as a limit-seeking, non-malicious, manual activity, which depends highly on a team-effort and an alchemist mindset. It is highly intrinsically motivated by curiosity, fun, and to some degrees by concerns for various harms of deploying LLMs. We identify a taxonomy of 12 strategies and 35 different techniques of attacking LLMs. These findings are presented as a comprehensive grounded theory of how and why people attack large language models: LLM red teaming.
In this paper, we introduce BiMediX, the first bilingual medical mixture of experts LLM designed for seamless interaction in both English and Arabic. Our model facilitates a wide range of medical interactions in English and Arabic, including multi-turn chats to inquire about additional details such as patient symptoms and medical history, multiple-choice question answering, and open-ended question answering. We propose a semi-automated English-to-Arabic translation pipeline with human refinement to ensure high-quality translations. We also introduce a comprehensive evaluation benchmark for Arabic medical LLMs. Furthermore, we introduce BiMed1.3M, an extensive Arabic-English bilingual instruction set covering 1.3 Million diverse medical interactions, resulting in over 632 million healthcare specialized tokens for instruction tuning. Our BiMed1.3M dataset includes 250k synthesized multi-turn doctor-patient chats and maintains a 1:2 Arabic-to-English ratio. Our model outperforms state-of-the-art Med42 and Meditron by average absolute gains of 2.5% and 4.1%, respectively, computed across multiple medical evaluation benchmarks in English, while operating at 8-times faster inference. Moreover, our BiMediX outperforms the generic Arabic-English bilingual LLM, Jais-30B, by average absolute gains of 10% on our Arabic medical benchmark and 15% on bilingual evaluations across multiple datasets. Our project page with source code and trained model is available at https://github.com/mbzuai-oryx/BiMediX .
We consider the problem of model compression for Large Language Models (LLMs) at post-training time, where the task is to compress a well-trained model using only a small set of calibration input data. In this work, we introduce a new low-rank approach to correct for quantization errors of \emph{activations} in LLMs: we propose to add low-rank weight matrices in full precision that act on the \emph{unquantized} activations. We then solve a joint optimization problem over the quantized representation of the weights and additional low-rank weight matrices to quantize both weights and activations. We focus on the case of 4-bit weight-and-activation quantization (W4A4). Using ranks equivalent to 10\% of the original weight matrix size, our approach reduces the accuracy gap with the original model by more than 50\%. Using ranks equivalent to 30\% of the original weight matrix, the accuracy gap is closed completely. We demonstrate our results on four recent LLMs, namely Llama-2, Llama-3, Phi-3 and Mixtral models.
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work proposed advanced prompting techniques and the necessity of fine-tuning with high-quality data to augment LLMs' reasoning abilities. However, these approaches are inherently constrained by data availability and quality. In light of this, self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn from self-assessed rewards. Yet, the efficacy of LLMs in self-refining its response, particularly in complex reasoning and planning task, remains dubious. In this paper, we introduce AlphaLLM for the self-improvements of LLMs, which integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop, thereby enhancing the capabilities of LLMs without additional annotations. Drawing inspiration from the success of AlphaGo, AlphaLLM addresses the unique challenges of combining MCTS with LLM for self-improvement, including data scarcity, the vastness search spaces of language tasks, and the subjective nature of feedback in language tasks. AlphaLLM is comprised of prompt synthesis component, an efficient MCTS approach tailored for language tasks, and a trio of critic models for precise feedback. Our experimental results in mathematical reasoning tasks demonstrate that AlphaLLM significantly enhances the performance of LLMs without additional annotations, showing the potential for self-improvement in LLMs.
Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been proposed, they often require access to the model's internal structure or need additional training, which is impractical for service providers using LLM APIs, such as OpenAI APIs or Claude APIs. In this paper, we propose a moving target defense approach that alters decoding hyperparameters to enhance model robustness against various jailbreak attacks. Our approach does not require access to the model's internal structure and incurs no additional training costs. The proposed defense includes two key components: (1) optimizing the decoding strategy by identifying and adjusting decoding hyperparameters that influence token generation probabilities, and (2) transforming the decoding hyperparameters and model system prompts into dynamic targets, which are continuously altered during each runtime. By continuously modifying decoding strategies and prompts, the defense effectively mitigates the existing attacks. Our results demonstrate that our defense is the most effective against jailbreak attacks in three of the models tested when using LLMs as black-box APIs. Moreover, our defense offers lower inference costs and maintains comparable response quality, making it a potential layer of protection when used alongside other defense methods.
Existing Hardware Trojans (HT) detection methods face several critical limitations: logic testing struggles with scalability and coverage for large designs, side-channel analysis requires golden reference chips, and formal verification methods suffer from state-space explosion. The emergence of Large Language Models (LLMs) offers a promising new direction for HT detection by leveraging their natural language understanding and reasoning capabilities. For the first time, this paper explores the potential of general-purpose LLMs in detecting various HTs inserted in Register Transfer Level (RTL) designs, including SRAM, AES, and UART modules. We propose a novel tool for this goal that systematically assesses state-of-the-art LLMs (GPT-4o, Gemini 1.5 pro, and Llama 3.1) in detecting HTs without prior fine-tuning. To address potential training data bias, the tool implements perturbation techniques, i.e., variable name obfuscation, and design restructuring, that make the cases more sophisticated for the used LLMs. Our experimental evaluation demonstrates perfect detection rates by GPT-4o and Gemini 1.5 pro in baseline scenarios (100%/100% precision/recall), with both models achieving better trigger line coverage (TLC: 0.82-0.98) than payload line coverage (PLC: 0.32-0.46). Under code perturbation, while Gemini 1.5 pro maintains perfect detection performance (100%/100%), GPT-4o (100%/85.7%) and Llama 3.1 (66.7%/85.7%) show some degradation in detection rates, and all models experience decreased accuracy in localizing both triggers and payloads. This paper validates the potential of LLM approaches for hardware security applications, highlighting areas for future improvement.
As LLMs increase in accessibility, LLM-generated texts have proliferated across several fields, such as scientific, academic, and creative writing. However, LLMs are not created equally; they may have different architectures and training datasets. Thus, some LLMs may be more challenging to detect than others. Using two datasets spanning four total writing domains, we train AI-generated (AIG) text classifiers using the LibAUC library - a deep learning library for training classifiers with imbalanced datasets. Our results in the Deepfake Text dataset show that AIG-text detection varies across domains, with scientific writing being relatively challenging. In the Rewritten Ivy Panda (RIP) dataset focusing on student essays, we find that the OpenAI family of LLMs was substantially difficult for our classifiers to distinguish from human texts. Additionally, we explore possible factors that could explain the difficulties in detecting OpenAI-generated texts.
Performing complex manipulation tasks in dynamic environments requires efficient Task and Motion Planning (TAMP) approaches, which combine high-level symbolic plan with low-level motion planning. Advances in Large Language Models (LLMs), such as GPT-4, are transforming task planning by offering natural language as an intuitive and flexible way to describe tasks, generate symbolic plans, and reason. However, the effectiveness of LLM-based TAMP approaches is limited due to static and template-based prompting, which struggles in adapting to dynamic environments and complex task contexts. To address these limitations, this work proposes a novel ontology-driven prompt-tuning framework that employs knowledge-based reasoning to refine and expand user prompts with task contextual reasoning and knowledge-based environment state descriptions. Integrating domain-specific knowledge into the prompt ensures semantically accurate and context-aware task plans. The proposed framework demonstrates its effectiveness by resolving semantic errors in symbolic plan generation, such as maintaining logical temporal goal ordering in scenarios involving hierarchical object placement. The proposed framework is validated through both simulation and real-world scenarios, demonstrating significant improvements over the baseline approach in terms of adaptability to dynamic environments, and the generation of semantically correct task plans.
Ensemble reasoning for the strengths of different LLM experts is critical to achieving consistent and satisfactory performance on diverse inputs across a wide range of tasks. However, existing LLM ensemble methods are either computationally intensive or incapable of leveraging complementary knowledge among LLM experts for various inputs. In this paper, we propose a Dynamic Ensemble Reasoning paradigm, called DER to integrate the strengths of multiple LLM experts conditioned on dynamic inputs. Specifically, we model the LLM ensemble reasoning problem as a Markov Decision Process (MDP), wherein an agent sequentially takes inputs to request knowledge from an LLM candidate and passes the output to a subsequent LLM candidate. Moreover, we devise a reward function to train a DER-Agent to dynamically select an optimal answering route given the input questions, aiming to achieve the highest performance with as few computational resources as possible. Last, to fully transfer the expert knowledge from the prior LLMs, we develop a Knowledge Transfer Prompt (KTP) that enables the subsequent LLM candidates to transfer complementary knowledge effectively. Experiments demonstrate that our method uses fewer computational resources to achieve better performance compared to state-of-the-art baselines.
We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
Large language models (LLMs) are enabling designers to give life to exciting new user experiences for information access. In this work, we present a system that generates LLM personas to debate a topic of interest from different perspectives. How might information seekers use and benefit from such a system? Can centering information access around diverse viewpoints help to mitigate thorny challenges like confirmation bias in which information seekers over-trust search results matching existing beliefs? How do potential biases and hallucinations in LLMs play out alongside human users who are also fallible and possibly biased? Our study exposes participants to multiple viewpoints on controversial issues via a mixed-methods, within-subjects study. We use eye-tracking metrics to quantitatively assess cognitive engagement alongside qualitative feedback. Compared to a baseline search system, we see more creative interactions and diverse information-seeking with our multi-persona debate system, which more effectively reduces user confirmation bias and conviction toward their initial beliefs. Overall, our study contributes to the emerging design space of LLM-based information access systems, specifically investigating the potential of simulated personas to promote greater exposure to information diversity, emulate collective intelligence, and mitigate bias in information seeking.
The pervasive spread of misinformation and disinformation in social media underscores the critical importance of detecting media bias. While robust Large Language Models (LLMs) have emerged as foundational tools for bias prediction, concerns about inherent biases within these models persist. In this work, we investigate the presence and nature of bias within LLMs and its consequential impact on media bias detection. Departing from conventional approaches that focus solely on bias detection in media content, we delve into biases within the LLM systems themselves. Through meticulous examination, we probe whether LLMs exhibit biases, particularly in political bias prediction and text continuation tasks. Additionally, we explore bias across diverse topics, aiming to uncover nuanced variations in bias expression within the LLM framework. Importantly, we propose debiasing strategies, including prompt engineering and model fine-tuning. Extensive analysis of bias tendencies across different LLMs sheds light on the broader landscape of bias propagation in language models. This study advances our understanding of LLM bias, offering critical insights into its implications for bias detection tasks and paving the way for more robust and equitable AI systems
Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are largely sample-specific, relying on manually crafted or discretely optimized memory-inducing prompts generated on a per-sample basis, which become impractical for dataset-level detection due to the prohibitive computational cost of iterating over all samples. In real-world scenarios, data owners may need to verify whether a susceptible LLM has memorized their dataset, particularly if the LLM may have collected the data from the web without authorization. To address this, we introduce \textit{MemHunter}, which trains a memory-inducing LLM and employs hypothesis testing to efficiently detect memorization at the dataset level, without requiring sample-specific memory inducing. Experiments on models such as Pythia and Llama-2 demonstrate that \textit{MemHunter} can extract up to 40\% more training data than existing methods under constrained time resources and reduce search time by up to 80\% when integrated as a plug-in. Crucially, \textit{MemHunter} is the first method capable of dataset-level memorization detection, providing an indispensable tool for assessing privacy risks in LLMs that are powered by vast web-sourced datasets.
Continual Semantic Parsing (CSP) aims to train parsers to convert natural language questions into SQL across tasks with limited annotated examples, adapting to the real-world scenario of dynamically updated databases. Previous studies mitigate this challenge by replaying historical data or employing parameter-efficient tuning (PET), but they often violate data privacy or rely on ideal continual learning settings. To address these problems, we propose a new Large Language Model (LLM)-Enhanced Continuous Semantic Parsing method, named LECSP, which alleviates forgetting while encouraging generalization, without requiring real data replay or ideal settings. Specifically, it first analyzes the commonalities and differences between tasks from the SQL syntax perspective to guide LLMs in reconstructing key memories and improving memory accuracy through a calibration strategy. Then, it uses a task-aware dual-teacher distillation framework to promote the accumulation and transfer of knowledge during sequential training. Experimental results on two CSP benchmarks show that our method significantly outperforms existing methods, even those utilizing data replay or ideal settings. Additionally, we achieve generalization performance beyond the upper limits, better adapting to unseen tasks.
Reinforcement learning from human feedback (RLHF) is one of the key techniques that helps large language models (LLMs) to follow instructions and provide helpful and harmless responses. While direct policy optimization methods exist, state-of-the-art LLMs adopt RL-based methods (usually PPO) in RLHF to train the policy to generate good responses guided by a reward model learned from preference data. The main challenge of these methods is the inaccuracy of the intermediate reward model, especially in code generation tasks that require long and complex reasoning to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtration strategy for a given reward model, the coefficient of determination ($R^2$) between rewards and actual scores on filtered samples serves as a good metrics and helps us find several promising strategies. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation tasks, and find that some variants of PF-PPO are highly effective and achieve new state-of-the-art performance across 7-billion-parameter models on HumanEval, MBPP, and a new and more challenging LeetCode Contest benchmark.
The rapid advancement of Large Language Models (LLMs) has driven their expanding application across various fields. One of the most promising applications is their role as evaluators based on natural language responses, referred to as ''LLMs-as-judges''. This framework has attracted growing attention from both academia and industry due to their excellent effectiveness, ability to generalize across tasks, and interpretability in the form of natural language. This paper presents a comprehensive survey of the LLMs-as-judges paradigm from five key perspectives: Functionality, Methodology, Applications, Meta-evaluation, and Limitations. We begin by providing a systematic definition of LLMs-as-Judges and introduce their functionality (Why use LLM judges?). Then we address methodology to construct an evaluation system with LLMs (How to use LLM judges?). Additionally, we investigate the potential domains for their application (Where to use LLM judges?) and discuss methods for evaluating them in various contexts (How to evaluate LLM judges?). Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions. Through a structured and comprehensive analysis, we aim aims to provide insights on the development and application of LLMs-as-judges in both research and practice. We will continue to maintain the relevant resource list at https://github.com/CSHaitao/Awesome-LLMs-as-Judges.
Extracting relevant and structured knowledge from large, complex technical documents within the Reliability and Maintainability (RAM) domain is labor-intensive and prone to errors. Our work addresses this challenge by presenting OntoKGen, a genuine pipeline for ontology extraction and Knowledge Graph (KG) generation. OntoKGen leverages Large Language Models (LLMs) through an interactive user interface guided by our adaptive iterative Chain of Thought (CoT) algorithm to ensure that the ontology extraction process and, thus, KG generation align with user-specific requirements. Although KG generation follows a clear, structured path based on the confirmed ontology, there is no universally correct ontology as it is inherently based on the user's preferences. OntoKGen recommends an ontology grounded in best practices, minimizing user effort and providing valuable insights that may have been overlooked, all while giving the user complete control over the final ontology. Having generated the KG based on the confirmed ontology, OntoKGen enables seamless integration into schemeless, non-relational databases like Neo4j. This integration allows for flexible storage and retrieval of knowledge from diverse, unstructured sources, facilitating advanced querying, analysis, and decision-making. Moreover, the generated KG serves as a robust foundation for future integration into Retrieval Augmented Generation (RAG) systems, offering enhanced capabilities for developing domain-specific intelligent applications.
The colossal parameters and computational overhead of Large Language Models (LLMs) challenge their real-world applications. Network pruning, which targets unstructured or structured sparsity by removing redundant parameters, has recently been explored for LLM acceleration. Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up. In contrast, structured pruning can reduce latency on general devices. However, it remains a challenge to perform structured pruning efficiently and maintain performance, especially at high sparsity ratios. To this end, we introduce an efficient structured pruning framework named CFSP, which leverages both Coarse (interblock) and Fine-grained (intrablock) activation information as an importance criterion to guide pruning. The pruning is highly efficient, as it only requires one forward pass to compute feature activations. Specifically, we first allocate the sparsity budget across blocks based on their importance and then retain important weights within each block. In addition, we introduce a recovery fine-tuning strategy that adaptively allocates training overhead based on coarse-grained importance to further improve performance. Experimental results demonstrate that CFSP outperforms existing methods on diverse models across various sparsity budgets. Our code will be available at https://github.com/wyxscir/CFSP.
Large Language Models (LLMs) have demonstrated notable proficiency in both code generation and comprehension across multiple programming languages. However, the mechanisms underlying this proficiency remain underexplored, particularly with respect to whether distinct programming languages are processed independently or within a shared parametric region. Drawing an analogy to the specialized regions of the brain responsible for distinct cognitive functions, we introduce the concept of Coding Spot, a specialized parametric region within LLMs that facilitates coding capabilities. Our findings identify this Coding Spot and show that targeted modifications to this subset significantly affect performance on coding tasks, while largely preserving non-coding functionalities. This compartmentalization mirrors the functional specialization observed in cognitive neuroscience, where specific brain regions are dedicated to distinct tasks, suggesting that LLMs may similarly employ specialized parameter regions for different knowledge domains.
While scaling laws optimize training configurations for large language models (LLMs) through experiments on smaller or early-stage models, they fail to predict emergent abilities due to the absence of such capabilities in these models. To address this, we propose a method that predicts emergent abilities by leveraging proxy tasks. We begin by establishing relevance metrics between the target task and candidate tasks based on performance differences across multiple models. These candidate tasks are then validated for robustness with small model ensembles, leading to the selection of the most appropriate proxy tasks. The predicted performance on the target task is then derived by integrating the evaluation results of these proxies. In a case study on tool utilization capabilities, our method demonstrated a strong correlation between predicted and actual performance, confirming its effectiveness.
Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.
Test oracles play a crucial role in software testing, enabling effective bug detection. Despite initial promise, neural-based methods for automated test oracle generation often result in a large number of false positives and weaker test oracles. While LLMs have demonstrated impressive effectiveness in various software engineering tasks, including code generation, test case creation, and bug fixing, there remains a notable absence of large-scale studies exploring their effectiveness in test oracle generation. The question of whether LLMs can address the challenges in effective oracle generation is both compelling and requires thorough investigation. In this research, we present the first comprehensive study to investigate the capabilities of LLMs in generating correct, diverse, and strong test oracles capable of effectively identifying a large number of unique bugs. To this end, we fine-tuned seven code LLMs using six distinct prompts on the SF110 dataset. Utilizing the most effective fine-tuned LLM and prompt pair, we introduce TOGLL, a novel LLM-based method for test oracle generation. To investigate the generalizability of TOGLL, we conduct studies on 25 large-scale Java projects. Besides assessing the correctness, we also assess the diversity and strength of the generated oracles. We compare the results against EvoSuite and the state-of-the-art neural method, TOGA. Our findings reveal that TOGLL can produce 3.8 times more correct assertion oracles and 4.9 times more exception oracles. Moreover, our findings demonstrate that TOGLL is capable of generating significantly diverse test oracles. It can detect 1,023 unique bugs that EvoSuite cannot, which is ten times more than what the previous SOTA neural-based method, TOGA, can detect.
Large language models (LLMs) use function calls to interface with external tools and data source. However, the current approach to LLM function calling is inherently synchronous, where each call blocks LLM inference, limiting LLM operation and concurrent function execution. In this work, we propose AsyncLM, a system for asynchronous LLM function calling. AsyncLM improves LLM's operational efficiency by enabling LLMs to generate and execute function calls concurrently. Instead of waiting for each call's completion, AsyncLM introduces an interrupt mechanism to asynchronously notify the LLM in-flight when function calls return. We design an in-context protocol for function calls and interrupts, provide fine-tuning strategy to adapt LLMs to the interrupt semantics, and implement these mechanisms efficiently on LLM inference process. We demonstrate that AsyncLM can reduce end-to-end task completion latency from 1.6x-5.4x compared to synchronous function calling on a set of benchmark tasks in the Berkeley function calling leaderboard (BFCL). Furthermore, we discuss how interrupt mechanisms can be extended to enable novel human-LLM or LLM-LLM interactions.
Mental health disorders are increasingly prevalent worldwide, creating an urgent need for innovative tools to support early diagnosis and intervention. This study explores the potential of Large Language Models (LLMs) in multimodal mental health diagnostics, specifically for detecting depression and Post Traumatic Stress Disorder through text and audio modalities. Using the E-DAIC dataset, we compare text and audio modalities to investigate whether LLMs can perform equally well or better with audio inputs. We further examine the integration of both modalities to determine if this can enhance diagnostic accuracy, which generally results in improved performance metrics. Our analysis specifically utilizes custom-formulated metrics; Modal Superiority Score and Disagreement Resolvement Score to evaluate how combined modalities influence model performance. The Gemini 1.5 Pro model achieves the highest scores in binary depression classification when using the combined modality, with an F1 score of 0.67 and a Balanced Accuracy (BA) of 77.4%, assessed across the full dataset. These results represent an increase of 3.1% over its performance with the text modality and 2.7% over the audio modality, highlighting the effectiveness of integrating modalities to enhance diagnostic accuracy. Notably, all results are obtained in zero-shot inferring, highlighting the robustness of the models without requiring task-specific fine-tuning. To explore the impact of different configurations on model performance, we conduct binary, severity, and multiclass tasks using both zero-shot and few-shot prompts, examining the effects of prompt variations on performance. The results reveal that models such as Gemini 1.5 Pro in text and audio modalities, and GPT-4o mini in the text modality, often surpass other models in balanced accuracy and F1 scores across multiple tasks.
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive amount of text corpora, high-quality domain-specific text data can still significantly enhance ASR performance on domain adaptation tasks. Although LLM-based ASR can naturally incorporate more text corpora by fine-tuning the LLM decoder, fine-tuning such ASR on text-only data without paired prompts may diminish the effectiveness of domain-specific knowledge. To mitigate this issue, we propose a two-step soft prompt fine-tuning strategy that enhances domain-specific text adaptation. Experimental results show that text adaptation with our proposed method achieved a relative up to 9% Word Error Rate (WER) reduction and up to 18% Entity Error Rate (EER) reduction on the target domain compared to the baseline ASR. Combining this with domain-specific Language Model (LM) fusion can further improve the EER by a relative 2-5%
We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. Together, WildGuard serves the increasing needs for automatic safety moderation and evaluation of LLM interactions, providing a one-stop tool with enhanced accuracy and broad coverage across 13 risk categories. While existing open moderation tools such as Llama-Guard2 score reasonably well in classifying straightforward model interactions, they lag far behind a prompted GPT-4, especially in identifying adversarial jailbreaks and in evaluating models' refusals, a key measure for evaluating safety behaviors in model responses. To address these challenges, we construct WildGuardMix, a large-scale and carefully balanced multi-task safety moderation dataset with 92K labeled examples that cover vanilla (direct) prompts and adversarial jailbreaks, paired with various refusal and compliance responses. WildGuardMix is a combination of WildGuardTrain, the training data of WildGuard, and WildGuardTest, a high-quality human-annotated moderation test set with 5K labeled items covering broad risk scenarios. Through extensive evaluations on WildGuardTest and ten existing public benchmarks, we show that WildGuard establishes state-of-the-art performance in open-source safety moderation across all the three tasks compared to ten strong existing open-source moderation models (e.g., up to 26.4% improvement on refusal detection). Importantly, WildGuard matches and sometimes exceeds GPT-4 performance (e.g., up to 3.9% improvement on prompt harmfulness identification). WildGuard serves as a highly effective safety moderator in an LLM interface, reducing the success rate of jailbreak attacks from 79.8% to 2.4%.
This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material, in our case explanations of code examples. This research is a part of our larger effort to automate the assessment of students' freely generated responses, focusing specifically on their self-explanations of code examples during activities related to code comprehension. In this work, we experiment with zero-shot prompting, Supervised Fine-Tuning (SFT), and preference alignment of LLMs to identify gaps in students' self-explanation. With simple prompting, GPT-4 consistently outperformed LLaMA3 and Mistral in identifying gaps and misconceptions, as confirmed by human evaluations. Additionally, our results suggest that fine-tuned large language models are more effective at identifying gaps in students' explanations compared to zero-shot and few-shot prompting techniques. Furthermore, our findings show that the preference optimization approach using Odds Ratio Preference Optimization (ORPO) outperforms SFT in identifying gaps and misconceptions in students' code explanations.
The ability to wield tools was once considered exclusive to human intelligence, but it's now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert the human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot's tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.
We present a novel approach to generating mathematical conjectures using Large Language Models (LLMs). Focusing on the solubilizer, a relatively recent construct in group theory, we demonstrate how LLMs such as ChatGPT, Gemini, and Claude can be leveraged to generate conjectures. These conjectures are pruned by allowing the LLMs to generate counterexamples. Our results indicate that LLMs are capable of producing original conjectures that, while not groundbreaking, are either plausible or falsifiable via counterexamples, though they exhibit limitations in code execution.
To develop autonomous agents capable of executing complex, multi-step decision-making tasks as specified by humans in natural language, existing reinforcement learning approaches typically require expensive labeled datasets or access to real-time experimentation. Moreover, conventional methods often face difficulties in generalizing to unseen goals and states, thereby limiting their practical applicability. This paper presents TEDUO, a novel training pipeline for offline language-conditioned policy learning. TEDUO operates on easy-to-obtain, unlabeled datasets and is suited for the so-called in-the-wild evaluation, wherein the agent encounters previously unseen goals and states. To address the challenges posed by such data and evaluation settings, our method leverages the prior knowledge and instruction-following capabilities of large language models (LLMs) to enhance the fidelity of pre-collected offline data and enable flexible generalization to new goals and states. Empirical results demonstrate that the dual role of LLMs in our framework-as data enhancers and generalizers-facilitates both effective and data-efficient learning of generalizable language-conditioned policies.