{"total":202,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391,"area":"lr"},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353,"area":"lr"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270,"area":null},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256,"area":"lr"},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124,"area":null},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2305.13168","title":"LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities","created":"2023-05-22","cited_by_count":97,"area":"lr"},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2308.04026","title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","created":"2023-08-08","cited_by_count":88,"area":null},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"id":"2306.00020","title":"GPT4GEO: How a Language Model Sees the World's Geography","created":"2023-05-30","cited_by_count":68,"area":"wm"},{"id":"2409.14051","title":"GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion","created":"2024-09-21","cited_by_count":67,"area":"lr"},{"id":"2306.09841","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","created":"2023-06-16","cited_by_count":65,"area":"lr"},{"id":"2305.05862","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","created":"2023-05-10","cited_by_count":59,"area":null},{"id":"2308.10819","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","created":"2023-08-17","cited_by_count":59,"area":"safety"},{"id":"2306.11489","title":"Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling","created":"2023-06-20","cited_by_count":56,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2309.05898","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","created":"2023-09-12","cited_by_count":51,"area":null},{"id":"2310.15515","title":"Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation","created":"2023-10-24","cited_by_count":51,"area":null},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2310.17918","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","created":"2023-10-27","cited_by_count":51,"area":null},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51,"area":"lr"},{"id":"2402.11291","title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","created":"2024-02-17","cited_by_count":45,"area":"lr"},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2309.03126","title":"Everyone Deserves A Reward: Learning Customized Human Preferences","created":"2023-09-06","cited_by_count":43,"area":"alignment"},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2311.09022","title":"Exploring the Potential of Large Language Models in Computational Argumentation","created":"2023-11-15","cited_by_count":42,"area":null},{"id":"2311.07954","title":"A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning","created":"2023-11-14","cited_by_count":41,"area":"lr"},{"id":"2308.03762","title":"GPT-4 Can't Reason","created":"2023-07-21","cited_by_count":40,"area":"lr"},{"id":"2403.16812","title":"Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making","created":"2024-03-25","cited_by_count":38,"area":null},{"id":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2310.03951","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","created":"2023-10-06","cited_by_count":35,"area":null},{"id":"2402.16048","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","created":"2024-02-25","cited_by_count":34,"area":"lr"},{"id":"2405.13001","title":"Large Language Models for Education: A Survey","created":"2024-05-12","cited_by_count":34,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","cited_by_count":31,"area":"lr"},{"id":"2310.14573","title":"Exploring the Boundaries of GPT-4 in Radiology","created":"2023-10-23","cited_by_count":31,"area":null},{"id":"2410.03775","title":"Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge","created":"2024-10-03","cited_by_count":31,"area":null},{"id":"2308.12241","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","created":"2023-08-23","cited_by_count":30,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2307.09751","title":"Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community","created":"2023-07-19","cited_by_count":29,"area":null},{"id":"2405.01744","title":"ALCM: Autonomous LLM-Augmented Causal Discovery Framework","created":"2024-05-02","cited_by_count":29,"area":"lr"},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2310.01386","title":"Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench","created":"2023-10-02","cited_by_count":28,"area":null},{"id":"2312.11521","title":"Large Language Models are Complex Table Parsers","created":"2023-12-13","cited_by_count":28,"area":null},{"id":"2404.13340","title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","created":"2024-04-20","cited_by_count":28,"area":null},{"id":"2311.08045","title":"Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game","created":"2023-11-14","cited_by_count":27,"area":"alignment"},{"id":"2408.04655","title":"Strong and weak alignment of large language models with human values","created":"2024-08-05","cited_by_count":27,"area":"alignment"},{"id":"2311.06158","title":"Language Models can be Logical Solvers","created":"2023-11-10","cited_by_count":24,"area":"lr"},{"id":"2405.00402","title":"Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models","created":"2024-05-01","cited_by_count":24,"area":"lr"},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2409.17539","title":"Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22,"area":null},{"id":"2410.01428","title":"Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks","created":"2024-10-02","cited_by_count":22,"area":"lr"},{"id":"2502.04790","title":"S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency","created":"2025-02-07","cited_by_count":22,"area":"lr"},{"id":"2311.11689","title":"Causal Structure Learning Supervised by Large Language Model","created":"2023-11-20","cited_by_count":21,"area":null},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2308.12466","title":"Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis","created":"2023-08-23","cited_by_count":20,"area":null},{"id":"2405.16674","title":"Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"area":"lr"},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2310.09158","title":"Improving Large Language Models in Event Relation Logical Prediction","created":"2023-10-13","cited_by_count":17,"area":null},{"id":"2409.12126","title":"Linguini: A benchmark for language-agnostic linguistic reasoning","created":"2024-09-18","cited_by_count":17,"area":"lr"},{"id":"2502.13550","title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2405.11002","title":"Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection","created":"2024-05-17","cited_by_count":16,"area":null},{"id":"2407.00390","title":"Advancing Process Verification for Large Language Models via Tree-Based Preference Learning","created":"2024-06-29","cited_by_count":16,"area":"lr"},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2309.05076","title":"An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents","created":"2023-09-10","cited_by_count":15,"area":"agents"},{"id":"2311.07387","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14,"area":"lr"},{"id":"2307.02792","title":"What Should Data Science Education Do with Large Language Models?","created":"2023-07-06","cited_by_count":13,"area":null},{"id":"2304.14106","title":"ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time","created":"2023-04-27","cited_by_count":12,"area":null},{"id":"2502.07803","title":"Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment","created":"2025-02-05","cited_by_count":12,"area":"lr"},{"id":"2308.09217","title":"Conversational Ontology Alignment with ChatGPT","created":"2023-08-18","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2402.00262","title":"Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective","created":"2024-02-01","cited_by_count":11,"area":"agents"},{"id":"2403.01390","title":"Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering","created":"2024-03-03","cited_by_count":11,"area":"lr"},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2502.08080","title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2306.16638","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","created":"2023-06-29","cited_by_count":10,"area":null}],"next_cursor":"100"}