{"total":55,"rows":[{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310,"area":null},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2410.05952","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","created":"2024-10-08","cited_by_count":35,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2401.14019","title":"Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI","created":"2024-01-25","cited_by_count":18,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2410.10783","title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2502.13576","title":"Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2510.26384","title":"Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings","created":"2025-10-30","cited_by_count":11,"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":"2410.01106","title":"Statistical inference on black-box generative models in the data kernel perspective space","created":"2024-10-01","cited_by_count":9,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2406.16086","title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2508.11847","title":"Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings","created":"2025-08-16","cited_by_count":8,"area":null},{"id":"2602.07909","title":"SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization","created":"2026-02-08","cited_by_count":8,"area":null},{"id":"2510.17998","title":"SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2504.08781","title":"Efficient Evaluation of Large Language Models via Collaborative Filtering","created":"2025-04-05","cited_by_count":5,"area":null},{"id":"2510.04051","title":"Toward a unified framework for data-efficient evaluation of large language models","created":"2025-10-05","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":"2409.02228","title":"Unforgettable Generalization in Language Models","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2409.09249","title":"NovAScore: A New Automated Metric for Evaluating Document Level Novelty","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2410.13804","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2506.09813","title":"Metritocracy: Representative Metrics for Lite Benchmarks","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.00710","title":"Learning More from Less: Unlocking Internal Representations for Benchmark Compression","created":"2026-01-31","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":"2604.01418","title":"Cost-Efficient Estimation of General Abilities Across Benchmarks","created":"2026-04-01","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":"2605.07096","title":"Query-efficient model evaluation using cached responses","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.11209","title":"Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.07616","title":"Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2608.14425","title":"Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2506.13216","title":"Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law","created":"2025-06-16","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":"2606.01400","title":"Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2608.31108","title":"Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2510.09418","title":"Large Language Model Selection with Limited Annotations","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2604.09034","title":"The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.09665","title":"Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.11608","title":"PRISM: A Geometric Risk Bound for Decomposing Drift into Scale, Shape, and Head","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.29183","title":"TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","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":"2608.21382","title":"There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items","created":"2026-07-17","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":"2609.35113","title":"SymbolicArena: A Unified Infrastructure for Benchmark Distillation and Dynamic Evaluation in Symbolic Regression","created":"2026-09-28","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}],"next_cursor":null}