ORCE 解决了 LLM 置信度校准中的关键矛盾——既要准确又要可靠，做模型部署或安全评估的团队值得关注这个解耦思路。
大语言模型在回答错误时仍可能表现出高置信度，这限制了其在实际场景中的可靠部署。现有方法将答案生成与置信度估计联合优化，可能导致置信度对齐干扰答案准确性。ORCE 提出解耦框架：先生成答案，再基于固定问答对估计置信度，避免直接扰动答案生成过程。通过多次采样构建正确性似然代理，并采用基于排序的强化学习目标，使置信度与正确性概率对齐。实验表明，该方法在保持答案准确性的同时，显著提升了校准和失败预测性能。
ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world scenarios. Verbalized confidence, where models explicitly state their confidence in natural language, provides a flexible and user-facing uncertainty signal that can be applied even when token logits are unavailable. However, existing verbalized-confidence methods often optimize answer generation and confidence generation jointly, which can cause confidence-alignment objectives to interfere with answer accuracy. In this work, we propose a decoupled and order-aware framework for verbalized confidence calibration. Our method first generates an answer and then estimates confidence conditioned on the fixed question--answer pair, allowing confidence optimization without directly perturbing the answer-generation process. To align confidence with correctness likelihood, we construct a sampling-based surrogate from multiple model completions and optimize rank-based reinforcement learning objectives that encourage responses with higher estimated correctness likelihood to receive higher verbalized confidence. Experiments on reasoning and knowledge-intensive benchmarks show that our method improves calibration and failure prediction performance while largely preserving answer accuracy. These results demonstrate that verbalized confidence can be more reliably aligned by decoupling confidence estimation from answer generation and optimizing the relative ordering of confidence across responses.