{"total":22,"rows":[{"id":"2606.15474","title":"Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines","created":"2026-06-13","cited_by_count":8,"area":null},{"id":"2601.05420","title":"Efficient Inference for Noisy LLM-as-a-Judge Evaluation","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2604.22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2606.00093","title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2605.06939","title":"Bias and Uncertainty in LLM-as-a-Judge Estimation","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2512.05958","title":"MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2512.11150","title":"Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2604.23505","title":"Uncertainty Propagation in LLM-Based Systems","created":"2026-04-26","cited_by_count":3,"area":null},{"id":"2601.22336","title":"Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2605.07572","title":"Open-Ended Task Discovery via Bayesian Optimization","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2603.17172","title":"Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2607.18239","title":"SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2608.26638","title":"Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.05505","title":"SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2605.10202","title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.11200","title":"ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.00494","title":"Human-Anchored Factuality Evaluation with Strategic Annotation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.31857","title":"LLM Judge Validation Under Sparse Overlap: From Inference to Design","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.35815","title":"How to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.09229","title":"Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.15961","title":"Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18248","title":"Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}