{"total":19,"rows":[{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2609.23959","title":"Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model","created":"2026-09-21","cited_by_count":8,"area":null},{"id":"2511.07364","title":"Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2509.17730","title":"ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2508.14390","title":"REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2607.04332","title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2505.11731","title":"Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2604.09624","title":"Self-Calibrating Language Models via Test-Time Discriminative Distillation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.15588","title":"Calibrating LLMs with Semantic-level Reward","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.20740","title":"Reinforcement Learning over Predictive Distributions for LLM Regression","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2604.22110","title":"Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.19220","title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.12687","title":"From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.33721","title":"Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39111","title":"Bongard: Training Machine Intuition","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00381","title":"OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.09371","title":"The Confidence Game: Strategic Miscalibration in Human-AI Delegation","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}