{"total":19,"rows":[{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45,"area":null},{"id":"2602.00521","title":"Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory","created":"2026-01-31","cited_by_count":16,"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":"2508.18684","title":"FALCON: Transforming Cyber Threat Intelligence into Deployable IDS Rules with Self-Reflection","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2607.10380","title":"CAFE: A Compound-AI Factorial Evaluation Framework","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2609.25447","title":"Conduct Under Pressure: What Sixty Language Models Do When a User Pushes","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2511.03047","title":"Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2604.03257","title":"Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2607.08961","title":"NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.13840","title":"ASSERT: A Measurement Pipeline for GenAI Audits","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.02707","title":"Door-in-the-Face Requests and Refusal Behaviour in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.24516","title":"LLJ Cards: Best practices for the Use of LLMs as Judges","created":"2026-09-21","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":"2610.02492","title":"Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.19992","title":"SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}