{"list":"other","total":56,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171},{"id":"2410.12405","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","created":"2024-10-16","cited_by_count":149},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2402.14903","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","created":"2024-02-22","cited_by_count":115},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53},{"id":"2407.18940","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","created":"2024-07-10","cited_by_count":50},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49},{"id":"2309.09369","title":"Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles","created":"2023-09-17","cited_by_count":45},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45},{"id":"2406.13805","title":"WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia","created":"2024-06-19","cited_by_count":44},{"id":"2306.10062","title":"Revealing the structure of language model capabilities","created":"2023-06-14","cited_by_count":40},{"id":"2503.10694","title":"Medical Large Language Model Benchmarks Should Prioritize Construct Validity","created":"2025-03-12","cited_by_count":38},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32},{"id":"2503.06378","title":"General Scales Unlock AI Evaluation with Explanatory and Predictive Power","created":"2025-03-09","cited_by_count":31},{"id":"2406.06196","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","created":"2024-06-10","cited_by_count":28},{"id":"2310.11616","title":"Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?","created":"2023-10-17","cited_by_count":27},{"id":"1912.01172","title":"Value-laden Disciplinary Shifts in Machine Learning","created":"2019-12-03","cited_by_count":25},{"id":"2107.02278","title":"\"Garbage In, Garbage Out\" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?","created":"2021-07-05","cited_by_count":24},{"id":"2210.12152","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","created":"2022-10-21","cited_by_count":21},{"id":"2406.04214","title":"ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models","created":"2024-06-06","cited_by_count":19},{"id":"2505.05602","title":"HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics","created":"2025-05-08","cited_by_count":18},{"id":"2404.13940","title":"A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models","created":"2024-04-22","cited_by_count":15},{"id":"2412.05288","title":"StackEval: Benchmarking LLMs in Coding Assistance","created":"2024-11-21","cited_by_count":15},{"id":"2410.03502","title":"CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios","created":"2024-10-04","cited_by_count":9},{"id":"2410.07765","title":"GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps","created":"2024-10-10","cited_by_count":8}],"next_cursor":null}