在不确定性中思考：通过推理校准提升长形式生成的真实性
Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration
AI总结：
本文提出CURE框架，通过在声明层面教授模型处理不确定性，提升长形式生成的真实性。该方法通过多阶段训练流程对齐模型置信度与声明正确性，并在推理时选择性预测，实验表明其在事实准确性上优于现有基线。
摘要：
大型语言模型（LLMs）在长形式生成中常常出现幻觉。现有方法主要通过事后修订或强化学习（RL）与基于正确性的奖励来提高真实性，但未能教会模型估计其生成中哪些部分是可靠的。因此，模型仍可能自信地陈述错误的主张。近期推理领域的进展显著提升了LLM性能，并通过将校准纳入RL目标来估计置信度。然而，现有方法仍局限于整个响应的单一置信度，这对于长形式生成中不同声明的不确定性变化是不够的。为缓解这一问题，我们提出了CURE框架，通过教授LLMs在声明层面推理不确定性来提升长形式真实性。我们首先引入了一种声明意识推理协议，将输出结构化为原子声明并配以显式的置信度估计。然后我们开发了多阶段训练流程，对齐模型置信度与声明的正确性，然后优化事实性。最终校准的置信度进一步使模型能够选择性预测，在推理时避免不确定的声明。在四个长形式真实性基准测试中，实验表明CURE在事实准确性上优于竞争性的监督和RL基线，同时保持事实召回率。特别是，在传记生成中，它将声明层面的准确性提高了高达39.9%。这些增益伴随着改进的校准，如FactBench上的AUROC增加了16.0%。
英文摘要：
Large language models (LLMs) often hallucinate in long-form generation. Existing approaches mainly improve factuality through post-hoc revision or reinforcement learning (RL) with correctness-based rewards, but they do not teach the model to estimate which parts of its generation are reliable. As a result, models may still state incorrect claims confidently in their responses. Recent advances in reasoning have significantly improved LLM performance, and have been leveraged to estimate confidence by incorporating calibration into RL objectives. However, existing approaches remain limited to a single scalar confidence for the entire response, which is insufficient for long-form generation where uncertainty varies across individual claims. To mitigate this problem, we propose CURE, a framework that improves long-form factuality by teaching LLMs to reason about uncertainty at the claim level. We first introduce a Claim-Aware Reasoning Protocol, which structures outputs into atomic claims paired with explicit confidence estimates. We then develop a multi-stage training pipeline that aligns model confidence with claims' correctness and then optimizes on factuality. The resulting calibrated confidence further enables selective prediction, allowing the model to abstain from uncertain claims at inference time. Experiments on four long-form factuality benchmarks show that CURE consistently improves factual accuracy over competitive supervised and RL baselines, while maintaining factual recall. In particular, it improves claim-level accuracy by up to 39.9% on Biography generation. These gains are accompanied by improved calibration, as reflected by a 16.0% increase in AUROC on FactBench.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
