Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

• URL: http://arxiv.org/abs/2607.22098v1
• Date: Fri, 24 Jul 2026 08:48:17 GMT
• Title: Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
• Abstract summary: We propose REDE, a learning framework for denoising reasoning traces for hallucination detection.<n>Rede uses final-answer attention as an automatic supervision signal to shape the step-level representation space.<n>Experiments show that REDE consistently improves hallucination detection performance over competitive baselines.
• Score: 14.440332703001218
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Scalable Token-Level Hallucination Detection in Large Language Models [63.3426544914783]
  Internal hallucinations are difficult to detect in reasoning-intensive tasks.<n>We propose TokenHD, a holistic pipeline for training token-level hallucination detectors.
  arXiv  Detail & Related papers  (2026-05-12T16:47:40Z)
• Sanity Checks for Long-Form Hallucination Detection [6.501493411588847]
  Hallucination detection methods for large language models operate on chain-of-thought reasoning traces, yet it remains unclear whether they evaluate the reasoning itself or merely exploit surface correlates of the final answer.<n>We introduce a controlled-invariance methodology that exposes this distinction through two oracle tests: textscForce, which replaces each response's final answer with the ground truth while preserving the reasoning trace, and textscRemove, which strips answer-announcement steps while leaving the trajectory intact.<n>This reveals if their predictive power derives from answer-level artifacts rather than from the structure
  arXiv  Detail & Related papers  (2026-05-08T18:00:58Z)
• DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning [48.77865928715759]
  Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models.<n> hallucination remains a critical issue that hinders their reliability.<n>We propose DynHD that bridge these gaps from both spatial (token sequence) and temporal (denoising dynamics) perspectives.
  arXiv  Detail & Related papers  (2026-03-17T12:40:29Z)
• Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization [78.94590726578014]
  multimodal reasoning models (MLRMs) remain prone to hallucinations, and effective solutions are still underexplored.<n>We propose C3PO, a training-based mitigation framework comprising textbfCompression and textbfPreference textbfOptimization.
  arXiv  Detail & Related papers  (2026-02-03T11:00:55Z)
• Hallucination Begins Where Saliency Drops [18.189047289404325]
  hallucinations frequently arise when preceding output tokens exhibit low saliency toward the prediction of the next token.<n>We introduce LVLMs-Saliency, a gradient-aware diagnostic framework that quantifies the visual grounding strength of each output token.<n>Our method significantly reduces hallucination rates while preserving fluency and task performance, offering a robust and interpretable solution.
  arXiv  Detail & Related papers  (2026-01-28T05:50:52Z)
• Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping [31.704726867711955]
  We introduce Answer-agreement Representation Shaping (ARS), which learns detection-friendly trace-conditioned representations.<n>ARS generates counterfactual answers through small latent interventions.<n>ARS consistently improves detection and achieves substantial gains over strong baselines.
  arXiv  Detail & Related papers  (2026-01-24T13:47:51Z)
• Lost in the Noise: How Reasoning Models Fail with Contextual Distractors [57.31788955167306]
  Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information.<n>We introduce NoisyBench, a comprehensive benchmark that systematically evaluates model robustness across 11 datasets in RAG, reasoning, alignment, and tool-use tasks.<n>Our evaluation reveals a catastrophic performance drop of up to 80% in state-of-the-art models when faced with contextual distractors.
  arXiv  Detail & Related papers  (2026-01-12T05:43:51Z)
• TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models [49.83690850047884]
  hallucination problem in D-LLMs remains underexplored, limiting their reliability in real-world applications.<n>Existing hallucination detection methods are designed for AR-LLMs and rely on signals from single-step generation.<n>We propose TraceDet, a novel framework that explicitly leverages the intermediate denoising steps of D-LLMs for hallucination detection.
  arXiv  Detail & Related papers  (2025-09-30T02:01:10Z)
• ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs [50.18087419133284]
  hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations.<n>We introduce a novel metric, the ICR Score, which quantifies the contribution of modules to the hidden states' update.<n>We propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states.
  arXiv  Detail & Related papers  (2025-07-22T11:44:26Z)
• Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models [12.270274049887298]
  Reasoning traces can be redundant or logically inconsistent, making them a new source of hallucination.<n>Existing hallucination detection methods focus primarily on answer-level uncertainty.<n>We propose RACE, a novel framework specifically tailored for hallucination detection in LRMs.
  arXiv  Detail & Related papers  (2025-06-05T09:54:04Z)
• GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation [62.63014905981601]
  Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge.<n>Effective RAIT must address two key challenges: firstly, effectively reject unknown questions to minimize hallucinations; secondly, avoid over-refusal to ensure questions that can be correctly answered are not rejected.<n>GraIT employs gradient-driven sample selection to effectively minimize hallucinations and (2) introduces an adaptive weighting mechanism during fine-tuning to reduce the risk of over-refusal.
  arXiv  Detail & Related papers  (2025-02-09T14:11:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.