{"total":20,"rows":[{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2410.18653","title":"Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2506.18082","title":"Statistical Multicriteria Evaluation of LLM-Generated Text","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2504.18395","title":"Three Types of Calibration with Properties and their Semantic and Formal Relationships","created":"2025-04-25","cited_by_count":5,"area":null},{"id":"2605.15000","title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2602.00279","title":"Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2509.15356","title":"Predicting Language Models' Success at Zero-Shot Probabilistic Prediction","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2510.22363","title":"Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2601.19862","title":"Calibration without Ground Truth","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2608.01361","title":"High-Stakes Decisions with Language Models: Insights from Emergency Triage","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2605.27016","title":"How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2610.03998","title":"Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09164","title":"Training Language Models To Be Coherent Decision-Makers","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.17096","title":"Towards Universal Calibration for In-Context Classification","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}