深度隐式认知促进可靠推理链推理
Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning
AI总结：
本文提出利用模型内在真实性编码提升CoT推理的可靠性，通过置信度预测器和束搜索优化推理路径，显著提高数学、符号和常识推理任务的准确性和可靠性。
摘要：
推理链（CoT）推理在大型语言模型（LLMs）和多模态大型语言模型（MLLMs）中展现了显著的深度推理能力。然而，其可靠性常受到中间步骤累积误差的影响。本文介绍了一种新的方法，通过利用模型的内在真实性编码来校准CoT推理的准确性。我们发现，特定的注意力头激活能够可靠地反映推理步骤的真实性。基于这一发现，我们训练了一个置信度预测器，利用这些对真实性敏感的激活来评估每个推理步骤的正确性，并通过束搜索动态选择最可能的推理路径。实验结果表明，我们的方法在数学、符号和常识推理任务中显著优于最先进的基线（例如Few-Shot CoT、Self-Consistency和Self-Evaluation Guided Beam Search），在单模态和多模态设置中均表现出更高的准确性和可靠性。我们进一步在大型推理模型上验证了该方法，确认其在专用推理模型中的适用性。此外，我们探讨了模型自我校正能力在CoT推理中的作用。本工作为CoT推理提供了新的可靠性提升路径，具有广泛的应用潜力。
英文摘要：
Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However, its reliability is often undermined by the accumulation of errors in intermediate steps. This paper introduces an novel approach to calibrate the CoT reasoning accuracy by leveraging the model's intrinsic veracity encoding. We discover that specific attention head activations reliably reflect the truthfulness of reasoning steps in CoT. Based on this insight, we train a confidence predictor to evaluate the correctness of each reasoning step using these truthfulness-sensitive activations, dynamically selecting the most plausible reasoning path via beam search. Experimental results demonstrate that our method significantly outperforms the state-of-the-art baselines (e.g., Few-Shot CoT, Self-Consistency, and Self-Evaluation Guided Beam Search) across the mathematical, symbolic, and commonsense reasoning tasks, exhibiting superior accuracy and reliability in both unimodal and multimodal settings. We further validate the approach on large reasoning models, confirming its applicability to specialized reasoning models. Additionally, we explore the role of the model's self-correction ability in CoT reasoning. This work provides a novel reliability improvement path for CoT reasoning with broad application potential.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
