{"list":"other","total":87,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"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":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117},{"id":"2308.13149","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","created":"2023-08-25","cited_by_count":115},{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101},{"id":"2312.14890","title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes","created":"2023-12-22","cited_by_count":79},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65},{"id":"2312.12343","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","created":"2023-12-19","cited_by_count":58},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54},{"id":"2412.13670","title":"AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge","created":"2024-12-18","cited_by_count":44},{"id":"2411.07140","title":"Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models","created":"2024-11-11","cited_by_count":43},{"id":"2412.15194","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","created":"2024-12-19","cited_by_count":41},{"id":"2502.14296","title":"On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective","created":"2025-02-20","cited_by_count":41},{"id":"2404.03647","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","created":"2024-04-04","cited_by_count":37},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30},{"id":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29},{"id":"2501.14275","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","created":"2025-01-24","cited_by_count":29},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25},{"id":"2309.04369","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","created":"2023-09-08","cited_by_count":24},{"id":"2403.00393","title":"TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs","created":"2024-03-01","cited_by_count":24},{"id":"2402.08100","title":"Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation","created":"2024-02-12","cited_by_count":21},{"id":"2406.13990","title":"Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation","created":"2024-06-20","cited_by_count":19},{"id":"2409.10280","title":"ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code","created":"2024-09-16","cited_by_count":19},{"id":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17},{"id":"2402.13125","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","created":"2024-02-20","cited_by_count":14},{"id":"2412.10424","title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","created":"2024-12-10","cited_by_count":13},{"id":"2406.04197","title":"DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning","created":"2024-06-06","cited_by_count":11},{"id":"2408.03281","title":"StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation","created":"2024-08-06","cited_by_count":9},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7},{"id":"2501.02863","title":"Beyond Pass or Fail: Multi-Dimensional Benchmarking of Foundation Models for Goal-based Mobile UI Navigation","created":"2025-01-06","cited_by_count":3}],"next_cursor":null}