REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models

arXiv:2508.14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical applications. Existing prompt-based methods treat calibration largely as a one-shot inference problem, relying on either instance-level reasoning or post-hoc self-assessment. We introduce Rehearse (Experiential Rehearsal), a training-free method that instead enables models to adapt from their own scored confidence experience. In a credence-calibration game grounded in a strictly proper scoring rule, the model receives feedback on prior confidence decisions; this experience is summarized in a post-game trajectory prefix that captures systematic over- or under-confidence. At inference time, the model applies this cross-instance calibration signal to the chain-of-thought reasoning trace for each new question. Across four LLMs, three benchmarks, and five random seeds, Rehearse achieves the lowest average ECE among training-free methods with improved accuracy, reducing average ECE by 58% relative to the uncalibrated baseline. Code is available at https://anonymous.4open.science/r/Experiential-Rehearsal-7C77/.

Related

• Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
• Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
• VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

Source: arXiv cs.AI | 2026-08-14