{"total":17,"rows":[{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2103.05331","title":"Active Testing: Sample-Efficient Model Evaluation","created":"2021-03-09","cited_by_count":82,"area":null},{"id":"2202.06881","title":"Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation","created":"2022-02-14","cited_by_count":26,"area":null},{"id":"2402.07891","title":"Label-Efficient Model Selection for Text Generation","created":"2024-02-12","cited_by_count":19,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2508.09093","title":"Scaling Up Active Testing to Large Language Models","created":"2025-08-12","cited_by_count":13,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2501.04234","title":"Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks","created":"2025-01-08","cited_by_count":10,"area":null},{"id":"2401.14893","title":"A structured regression approach for evaluating model performance across intersectional subgroups","created":"2024-01-26","cited_by_count":9,"area":null},{"id":"2108.06514","title":"Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations","created":"2021-08-14","cited_by_count":5,"area":null},{"id":"2510.07959","title":"DISCO: Diversifying Sample Condensation for Efficient Model Evaluation","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2511.10661","title":"Sequential Bayesian Evaluation of Large Language Model Behavior","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2404.02314","title":"A Strong Baseline for Molecular Few-Shot Learning","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2602.07226","title":"Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2610.20514","title":"Bayesian Learning to Select Fair Classifiers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}