{"list":"other","total":55,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"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":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2301.09633","title":"Prediction-Powered Inference","created":"2023-01-23","cited_by_count":220},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2311.01453","title":"PPI++: Efficient Prediction-Powered Inference","created":"2023-11-02","cited_by_count":117},{"id":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"id":"2305.18466","title":"Test-Time Training on Nearest Neighbors for Large Language Models","created":"2023-05-29","cited_by_count":88},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86},{"id":"2103.05331","title":"Active Testing: Sample-Efficient Model Evaluation","created":"2021-03-09","cited_by_count":82},{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2310.17567","title":"Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models","created":"2023-10-26","cited_by_count":64},{"id":"2502.04313","title":"Great Models Think Alike and this Undermines AI Oversight","created":"2025-02-06","cited_by_count":58},{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57},{"id":"2005.00450","title":"Computing the Testing Error without a Testing Set","created":"2020-05-01","cited_by_count":54},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51},{"id":"2407.12844","title":"metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models","created":"2024-07-04","cited_by_count":39},{"id":"1905.12580","title":"Model Similarity Mitigates Test Set Overuse","created":"2019-05-29","cited_by_count":38},{"id":"2401.04757","title":"How predictable is language model benchmark performance?","created":"2024-01-09","cited_by_count":37},{"id":"2410.05952","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","created":"2024-10-08","cited_by_count":35},{"id":"2308.02575","title":"Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings","created":"2023-08-03","cited_by_count":34},{"id":"2301.09880","title":"Probabilistic Bilevel Coreset Selection","created":"2023-01-24","cited_by_count":27},{"id":"2202.06881","title":"Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation","created":"2022-02-14","cited_by_count":26},{"id":"2501.18251","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","created":"2025-01-30","cited_by_count":23},{"id":"2407.06172","title":"On Speeding Up Language Model Evaluation","created":"2024-07-08","cited_by_count":15},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10},{"id":"2505.20178","title":"No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference","created":"2025-05-26","cited_by_count":8},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7},{"id":"1612.06661","title":"Four lectures on probabilistic methods for data science","created":"2016-12-20","cited_by_count":5}],"next_cursor":null}