{"total":52,"rows":[{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","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":"2601.07767","title":"Are LLM Decisions Faithful to Verbal Confidence?","created":"2026-01-12","cited_by_count":8,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2509.24988","title":"Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2510.05431","title":"Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.24505","title":"CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2603.22120","title":"StreamingClaw Technical Report","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2607.11022","title":"When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2602.01532","title":"PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.08701","title":"Unified Multimodal Uncertain Inference","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"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":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.17293","title":"Beyond \"I Don't Know\": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.05122","title":"Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","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":"2607.10474","title":"Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards","created":"2026-07-11","cited_by_count":2,"area":null},{"id":"2601.04277","title":"Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.19862","title":"Calibration without Ground Truth","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","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":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.03731","title":"Conformal Language Modeling via Posterior Sampling","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.32012","title":"CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"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":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.20585","title":"Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent","created":"2026-05-13","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":"2610.03063","title":"HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03190","title":"Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.11135","title":"Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16318","title":"Strong yet Controllable LLM Abstention without Learning to Abstain","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17495","title":"A Sense of Proprioception in Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20401","title":"Training Language Models to Fail Gracefully","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}