推理去噪器：用於大型推理模型中幻覺檢測的推理軌跡去噪

摘要

大型推理模型（LRMs）在生成最終答案前會產出長串推理軌跡。儘管這些軌跡可能包含對幻覺檢測有用的信號，但利用它們並非易事，因為長軌跡中常夾雜雜訊步驟，模糊了與真實性評估相關的線索。本文識別出兩種常見的推理雜訊形式，即無關步驟與重複步驟，並證明兩者均顯著降低幻覺檢測效能。現有的信心分數型方法與單純的嵌入過濾法無法可靠區分雜訊步驟與資訊步驟。為解決此挑戰，我們提出REDE，一個用於對推理軌跡去噪以進行幻覺檢測的新型學習框架。具體而言，REDE利用最終答案注意力作為自動監督信號來塑造步驟層級的表示空間，產生能可靠識別並過濾雜訊步驟的精煉嵌入。REDE透過在移除雜訊步驟後的過濾推理軌跡上運作，可輕易整合至多種幻覺檢測器中。在多個推理基準上的廣泛實驗顯示，REDE相較於競爭基準方法能持續提升檢測效能。

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.