提出实时检测长链思维推理中幻觉的新方法
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
- 将幻觉视为随推理过程演化的潜在状态
- 通过累积前缀信号追踪整个推理轨迹的幻觉演化
- 支持实时、可解释的幻觉检测，适合长推理任务
长链思维（CoT）推理虽能提升大语言模型性能，但其中的幻觉常以细微形式出现并逐步传播。我们提出，长CoT中的幻觉应被理解为动态演变的潜在状态，而非一次性错误事件。因此，我们将步骤级幻觉判断视为局部观测，引入累积前缀级幻觉信号，以跟踪推理全过程的全局状态演化。该方法实现了长链思维推理中的流式幻觉检测，提供实时且可解释的证据。
原文摘要 · Abstract (English)
Long chain-of-thought (CoT) reasoning improves the performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps. We suggest that hallucination in long CoT reasoning is better understood as an evolving latent state rather than a one-off erroneous event. Accordingly, we treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level hallucination signal that tracks the global evolution of the reasoning state over the entire trajectory. Overall, our approach enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。