{"total":38,"rows":[{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205,"area":null},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148,"area":null},{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"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":"2504.10356","title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","created":"2025-04-14","cited_by_count":26,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2503.01747","title":"Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2506.18082","title":"Statistical Multicriteria Evaluation of LLM-Generated Text","created":"2025-06-22","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":"2502.01754","title":"Evaluation of Large Language Models via Coupled Token Generation","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7,"area":null},{"id":"2605.30315","title":"Resolution Diagnostics for Paired LLM Evaluation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2607.03436","title":"What Does a Routing Oracle Measure Under Stochastic Decoding? Coupling, Scorer Choice, and Single-Commit Ceilings","created":"2026-07-03","cited_by_count":5,"area":null},{"id":"2506.00204","title":"Structure-Aware Fill-in-the-Middle Pretraining for Code","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2608.11323","title":"Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","cited_by_count":3,"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":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2412.04277","title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","created":"2024-12-05","cited_by_count":1,"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":"2512.21080","title":"LLM Personas as a Substitute for Field Experiments in Method Benchmarking","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2603.08924","title":"Quantifying Uncertainty in AI Visibility: A Statistical Framework for Generative Search Measurement","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.23114","title":"A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2607.25257","title":"Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.00482","title":"Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.17426","title":"Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.20487","title":"Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2610.15570","title":"Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}