{"list":"other","total":65,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"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":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2407.03978","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","created":"2024-07-04","cited_by_count":152},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114},{"id":"1906.04701","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","created":"2019-06-11","cited_by_count":101},{"id":"2404.05970","title":"Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation","created":"2024-04-09","cited_by_count":99},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2502.00561","title":"Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge","created":"2025-02-01","cited_by_count":63},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60},{"id":"2504.00698","title":"Command A: An Enterprise-Ready Large Language Model","created":"2025-04-01","cited_by_count":59},{"id":"2505.10573","title":"Measurement to Meaning: A Validity-Centered Framework for AI Evaluation","created":"2025-05-13","cited_by_count":57},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53},{"id":"2309.04269","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","created":"2023-09-08","cited_by_count":52},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45},{"id":"2505.08245","title":"Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement","created":"2025-05-13","cited_by_count":45},{"id":"2505.15055","title":"Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory","created":"2025-05-21","cited_by_count":45},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44},{"id":"2401.16788","title":"Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate","created":"2024-01-30","cited_by_count":41},{"id":"2503.10694","title":"Medical Large Language Model Benchmarks Should Prioritize Construct Validity","created":"2025-03-12","cited_by_count":38},{"id":"2410.17578","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","created":"2024-10-23","cited_by_count":35},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28},{"id":"2503.08893","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","created":"2025-03-11","cited_by_count":27},{"id":"2504.11900","title":"Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection","created":"2025-04-16","cited_by_count":24},{"id":"2504.01833","title":"YourBench: Easy Custom Evaluation Sets for Everyone","created":"2025-04-02","cited_by_count":20},{"id":"2501.13953","title":"Redundancy Principles for MLLMs Benchmarks","created":"2025-01-20","cited_by_count":19},{"id":"2407.12843","title":"NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions","created":"2024-07-04","cited_by_count":17},{"id":"2411.04424","title":"Bayesian Calibration of Win Rate Estimation with LLM Evaluators","created":"2024-11-07","cited_by_count":16},{"id":"2510.11822","title":"Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations","created":"2025-10-13","cited_by_count":16},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14},{"id":"2504.12558","title":"Benchmarking LLM-based Relevance Judgment Methods","created":"2025-04-17","cited_by_count":14},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9},{"id":"2510.07575","title":"Benchmarking is Broken -- Don't Let AI be its Own Judge","created":"2025-10-08","cited_by_count":8},{"id":"2506.15862","title":"MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers","created":"2025-06-18","cited_by_count":7},{"id":"2410.20833","title":"LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation","created":"2024-10-28","cited_by_count":5},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5},{"id":"2403.07762","title":"Supporting Annotators with Affordances for Efficiently Labeling Conversational Data","created":"2024-03-12","cited_by_count":3},{"id":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3},{"id":"2101.03237","title":"Learning to Emphasize: Dataset and Shared Task Models for Selecting Emphasis in Presentation Slides","created":"2021-01-02","cited_by_count":2},{"id":"2504.14039","title":"MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks","created":"2025-04-18","cited_by_count":2}],"next_cursor":null}