{"total":112,"rows":[{"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":"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":"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":"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":"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":"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":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"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":"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":"2310.17918","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":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"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":"2311.09022","title":"Exploring the Potential of Large Language Models in Computational Argumentation","created":"2023-11-15","cited_by_count":42,"area":null},{"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":"2310.03951","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","created":"2023-10-06","cited_by_count":35,"area":null},{"id":"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":"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":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"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":"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":"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":"2311.11689","title":"Causal Structure Learning Supervised by Large Language Model","created":"2023-11-20","cited_by_count":21,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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},{"id":"2401.16713","title":"Prospects for inconsistency detection using large language models and sheaves","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2403.03788","title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","created":"2024-03-06","cited_by_count":9,"area":null},{"id":"2312.03759","title":"How should the advent of large language models affect the practice of science?","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2403.14668","title":"Predicting Learning Performance with Large Language Models: A Study in Adult Literacy","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2408.05102","title":"How Well Do LLMs Identify Cultural Unity in Diversity?","created":"2024-08-09","cited_by_count":8,"area":null},{"id":"2305.14785","title":"Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2403.09705","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2309.06578","title":"Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences","created":"2023-09-07","cited_by_count":6,"area":null},{"id":"2402.17097","title":"Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2508.00719","title":"DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2305.06934","title":"Humans are Still Better than ChatGPT: Case of the IEEEXtreme Competition","created":"2023-05-10","cited_by_count":5,"area":null},{"id":"2306.04508","title":"Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2401.04218","title":"Distortions in Judged Spatial Relations in Large Language Models","created":"2024-01-08","cited_by_count":5,"area":null},{"id":"2404.06731","title":"Accuracy of a Large Language Model in Distinguishing Anti- And Pro-vaccination Messages on Social Media: The Case of Human Papillomavirus Vaccination","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2308.11189","title":"Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2311.10749","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2406.16779","title":"It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2505.12301","title":"Beyond Single-Point Judgment: Distribution Alignment for LLM-as-a-Judge","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2505.18638","title":"Multilingual Question Answering in Low-Resource Settings: A Dzongkha-English Benchmark for Foundation Models","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2310.17721","title":"From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2402.09750","title":"Pinning \"Reflection\" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding","created":"2024-02-15","cited_by_count":3,"area":null},{"id":"2402.19405","title":"Navigating Hallucinations for Reasoning of Unintentional Activities","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2406.12754","title":"Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2411.10325","title":"Bitcoin Research with a Transaction Graph Dataset","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2510.05486","title":"Language Model as Planner and Formalizer under Constraints","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2305.05377","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2307.07526","title":"Can I say, now machines can think?","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2401.07441","title":"Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2406.16611","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2503.05958","title":"SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2410.16640","title":"A Statistical Analysis of LLMs' Self-Evaluation Using Proverbs","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2501.12877","title":"WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2502.04797","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2504.12545","title":"Knowledge Acquisition on Mass-shooting Events via LLMs for AI-Driven Justice","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2312.10603","title":"Evaluating AI Vocational Skills Through Professional Testing","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2403.04771","title":"QASE Enhanced PLMs: Improved Control in Text Generation for MRC","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2404.04351","title":"Assisting humans in complex comparisons: automated information comparison at scale","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2404.17991","title":"Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension","created":"2024-04-27","cited_by_count":0,"area":null},{"id":"2405.00843","title":"Can a Hallucinating Model help in Reducing Human \"Hallucination\"?","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.01942","title":"CRCL at SemEval-2024 Task 2: Simple prompt optimizations","created":"2024-05-03","cited_by_count":0,"area":null}],"next_cursor":"100"}