{"total":82,"rows":[{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"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":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2410.05952","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","created":"2024-10-08","cited_by_count":35,"area":null},{"id":"2111.02275","title":"Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data","created":"2021-11-03","cited_by_count":28,"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":"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":"2301.10625","title":"Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment","created":"2023-01-25","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":"2406.10023","title":"Deep Bayesian Active Learning for Preference Modeling in Large Language Models","created":"2024-06-14","cited_by_count":19,"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":"2403.10175","title":"A Short Survey on Importance Weighting for Machine Learning","created":"2024-03-15","cited_by_count":15,"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":"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":"2609.24052","title":"Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)","created":"2026-09-21","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":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2603.27414","title":"Multiple-Prediction-Powered Inference","created":"2026-03-28","cited_by_count":9,"area":null},{"id":"2410.13609","title":"All models are wrong, some are useful: Model Selection with Limited Labels","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"area":null},{"id":"2507.23771","title":"Consensus-Driven Active Model Selection","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2510.10457","title":"Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?","created":"2025-10-12","cited_by_count":8,"area":null},{"id":"2603.18916","title":"Agentic Business Process Management: A Research Manifesto","created":"2026-03-19","cited_by_count":8,"area":"agents"},{"id":"2306.03151","title":"DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2502.09829","title":"Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2202.07652","title":"Predicting on the Edge: Identifying Where a Larger Model Does Better","created":"2022-02-15","cited_by_count":6,"area":null},{"id":"2211.12620","title":"Promises and Pitfalls of Threshold-based Auto-labeling","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2511.08991","title":"Robust Sampling for Active Statistical Inference","created":"2025-11-12","cited_by_count":6,"area":null},{"id":"2507.01372","title":"Active Measurement: Efficient Estimation at Scale","created":"2025-07-02","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":"2605.10075","title":"Active Testing of Large Language Models via Approximate Neyman Allocation","created":"2026-05-11","cited_by_count":5,"area":"lr"},{"id":"2608.20169","title":"Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection","created":"2026-08-20","cited_by_count":5,"area":null},{"id":"2109.12043","title":"Sample Efficient Model Evaluation","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2111.08861","title":"A label-efficient two-sample test","created":"2021-11-17","cited_by_count":4,"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":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2602.09411","title":"K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge","created":"2026-02-10","cited_by_count":4,"area":"alignment"},{"id":"2312.04740","title":"Train 'n Trade: Foundations of Parameter Markets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2402.05002","title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2603.21840","title":"Select, Label, Evaluate: Active Testing in NLP","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2210.10897","title":"Window-Based Distribution Shift Detection for Deep Neural Networks","created":"2022-10-19","cited_by_count":2,"area":null},{"id":"2402.06045","title":"Direct Acquisition Optimization for Low-Budget Active Learning","created":"2024-02-08","cited_by_count":2,"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":"2603.02029","title":"Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization","created":"2026-03-02","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":"2606.17541","title":"Offline Preference-Based Trajectory Evaluation","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2607.08522","title":"Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2609.17560","title":"Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds","created":"2026-07-22","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":"2505.22777","title":"MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2604.12951","title":"The Verification Tax: Fundamental Limits of AI Auditing in the Rare-Error Regime","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.24981","title":"Large Language Model Selection with Limited Annotations","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2607.14439","title":"Active Real-World Factor-Based Evaluation for Generalist Robot Policies","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2608.00423","title":"Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces","created":"2026-08-01","cited_by_count":1,"area":"inference"},{"id":"2609.19607","title":"DeltaSelect: Affordable A/B Testing for Coding Agents","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2210.00064","title":"CEREAL: Few-Sample Clustering Evaluation","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2212.08312","title":"An Efficient Framework for Monitoring Subgroup Performance of Machine Learning Systems","created":"2022-12-16","cited_by_count":0,"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":"2507.18123","title":"Actively evaluating and learning the distinctions that matter: Vaccine safety signal detection from emergency triage notes","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2510.09418","title":"Large Language Model Selection with Limited Annotations","created":"2025-10-10","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":"2602.07226","title":"Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators","created":"2026-02-06","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":"2607.17581","title":"Scalable Model-Assisted Multi-Target Estimation in Large Image Collections","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.27023","title":"BayesAME: Bayesian Active Model Evaluation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.01378","title":"When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.04388","title":"Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection","created":"2026-09-03","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":"2609.17956","title":"TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.18622","title":"How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27409","title":"Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference","created":"2026-09-23","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},{"id":"2609.32547","title":"Prioritizing Repeated LLM Evaluation for Hidden Failure Discovery","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37402","title":"Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38096","title":"Tail-Influence Sampling for CVaR Policy Evaluation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39026","title":"Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40190","title":"Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01592","title":"Which LLM to pick? Online Active Model Selection for Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}