推理去噪器：对推理轨迹进行去噪以检测大型推理模型中的幻觉

摘要

大型推理模型（LRMs）在生成最终答案前会产生长程推理轨迹。尽管这些轨迹可能包含用于幻觉检测的有用信号，但有效利用它们并非易事，因为长序列常包含噪声步骤，模糊了与真实性评估相关的线索。本文识别出两种常见的推理噪声形式——无关步骤与重复步骤，并表明两者均会显著降低幻觉检测性能。现有基于置信度的评分及朴素嵌入过滤方法难以可靠区分噪声步骤与信息性步骤。针对这一挑战，我们提出REDE，一种用于去噪推理轨迹的新型学习框架。具体而言，REDE利用最终答案注意力机制作为自动监督信号，构建步骤级表示空间，从而生成能够可靠识别并过滤噪声步骤的精炼嵌入。通过去除噪声步骤后的过滤推理轨迹，REDE可便捷嵌入多种幻觉检测器。在多个推理基准上的大量实验表明，REDE相较于竞争基线方法能持续提升检测性能。

English

Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for hallucination detection, harnessing them is non-trivial because long trajectories often include noisy steps that obscure the cues relevant to truthfulness assessment. In this paper, we identify two prevalent forms of reasoning noises, i.e., irrelevant steps and repetitive steps, and show that both substantially degrade hallucination detection performance. Existing confidence-based scores and naive embedding-based filtering fail to reliably separate noisy from informative steps. To address this challenge, we propose REDE, a novel learning framework for denoising reasoning traces for hallucination detection. Specifically, REDE leverages final-answer attention as an automatic supervision signal to shape the step-level representation space, yielding refined embeddings in which noisy steps can be reliably identified and filtered. REDE can be readily plugged into diverse hallucination detectors by operating on the filtered reasoning trajectory after removing noisy steps. Extensive experiments on multiple reasoning benchmarks show that REDE consistently improves detection performance over competitive baselines.