{"total":15,"rows":[{"id":"2502.05196","title":"LLMs Provide Unstable Answers to Legal Questions","created":"2025-01-28","cited_by_count":19,"area":null},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2504.21303","title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","created":"2025-04-30","cited_by_count":8,"area":null},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2601.06118","title":"Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism","created":"2026-01-03","cited_by_count":4,"area":null},{"id":"2506.08899","title":"Toward Robust Legal Text Formalization into Defeasible Deontic Logic using LLMs","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2510.03795","title":"Investigating LLM Variability in Personalized Conversational Information Retrieval","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2511.07722","title":"Critical Confabulation: Can LLMs Hallucinate for Social Good?","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2604.11261","title":"Inspectable AI for Science: A Research Object Approach to Generative AI Governance","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2509.22612","title":"Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask NLP evaluation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2602.02515","title":"CreditAudit: 2$^\\text{nd}$ Dimension for LLM Evaluation and Selection","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2609.15219","title":"From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle","created":"2026-09-14","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":"2610.09778","title":"Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}