{"total":16,"rows":[{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2503.09858","title":"Media and responsible AI governance: a game-theoretic and LLM analysis","created":"2025-03-12","cited_by_count":12,"area":null},{"id":"2508.20385","title":"CAPE: Context-Aware Personality Evaluation Framework for Large Language Models","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2505.15087","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2502.12052","title":"A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2509.07325","title":"CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2512.23711","title":"CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.07648","title":"What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.19529","title":"Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2505.17636","title":"Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.08320","title":"How Good LLM-Generated Password Policies Are?","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2605.03858","title":"MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2607.04419","title":"Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.12387","title":"Query Timing Produces Opposite Positional Biases Between LLMs and Humans","created":"2026-08-01","cited_by_count":0,"area":null}],"next_cursor":null}