{"total":23,"rows":[{"id":"2302.14545","title":"Modern Bayesian Experimental Design","created":"2023-02-28","cited_by_count":125,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"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":"2507.23771","title":"Consensus-Driven Active Model Selection","created":"2025-07-31","cited_by_count":8,"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":"2310.17044","title":"Learning to Rank for Active Learning via Multi-Task Bilevel Optimization","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2405.18911","title":"Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2602.00092","title":"Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2603.19264","title":"Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.23099","title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2505.07023","title":"Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2407.13000","title":"Novel Deep Neural Network Classifier Characterization Metrics with Applications to Dataless Evaluation","created":"2024-07-17","cited_by_count":0,"area":null},{"id":"2511.00964","title":"Using Synthetic Data to estimate the True Error is theoretically and practically doable","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2601.22326","title":"Label-Efficient Monitoring of Classification Models via Stratified Importance Sampling","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2606.02247","title":"ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2609.08399","title":"MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.25657","title":"Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.28560","title":"Speculative Evaluation of Stochastic LLMs","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}