让大模型自己发现并纠正幻觉，提升推理可靠性。
Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs
- 用自信度一致性和词元熵突增检测推理中的不可靠环节。
- 在多步推理中同时提升答案准确率与中间步骤的可信度。
- 适合需要高可信推理的医疗、法律等严谨场景使用。
本研究提出一种自校正框架，用于检测和缓解大语言模型在多步推理过程中的幻觉问题。不依赖最终答案的正确性，而是利用细粒度的不确定性信号：1）自我评估自信度的一致性，以及2）词元级别的熵突增，实时识别不可靠且不忠实的推理路径。设计复合奖励函数，惩罚无根据的高自信和熵突增，同时鼓励稳定准确的推理轨迹。这些信号引导强化学习策略，使模型更具内省能力，并通过感知自信度的奖励反馈调整生成行为，不仅提升结果准确性，也增强中间推理步骤的连贯性与忠实性。实验表明，该方法同时提升了最终答案的准确率与推理校准度，消融实验验证了每种信号的独立贡献。
原文摘要 · Abstract (English)
This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals: 1) self-assessed confidence alignment, and 2) token-level entropy spikes to detect unreliable and unfaithful reasoning in real time. We design a composite reward function that penalizes unjustified high confidence and entropy spikes, while encouraging stable and accurate reasoning trajectories. These signals guide a reinforcement learning (RL) policy that makes the model more introspective and shapes the model's generation behavior through confidence-aware reward feedback, improving not just outcome correctness but the coherence and faithfulness of their intermediate reasoning steps. Experiments show that our method improves both final answer accuracy and reasoning calibration, with ablations validating the individual contribution of each signal.
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。