一致思考，高效推理：面向隐式思维链的基于能量的校准
Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
AI总结：
本文提出EBM-CoT框架，利用基于能量的模型校准隐式思维链中的潜在推理轨迹，在不修改基础模型的前提下提升LLMs多步推理的一致性与效率。
摘要：
大型语言模型（LLMs）通过思维链（Chain-of-Thought, CoT）提示展现了强大的推理能力，该提示支持逐步的中间推理。然而，显式CoT方法依赖离散的token级推理过程，容易发生错误传播，并受限于词汇表达能力，常常导致僵化且不一致的推理轨迹。近期研究探索了在潜在空间中的隐式或连续推理，使模型能够在生成显式输出之前进行内部推理。尽管这类方法缓解了离散CoT的某些局限，但它们通常缺乏显式机制来强制推理步骤之间的一致性，从而导致发散性推理路径和不稳定的结果。为解决这一问题，我们提出了EBM-CoT，一个基于能量的思维链校准框架，通过基于能量的模型（EBM）来细化潜在思维表示。我们的方法动态地将潜在推理轨迹调整到嵌入空间中能量更低、一致性更高的区域，从而在不修改基础语言模型的情况下同时提升推理准确性和一致性。在数学、常识和符号推理基准上的大量实验表明，所提出的框架显著增强了LLMs中多步推理的一致性和效率。
英文摘要：
Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level reasoning processes that are prone to error propagation and limited by vocabulary expressiveness, often resulting in rigid and inconsistent reasoning trajectories. Recent research has explored implicit or continuous reasoning in latent spaces, allowing models to perform internal reasoning before generating explicit output. Although such approaches alleviate some limitations of discrete CoT, they generally lack explicit mechanisms to enforce consistency among reasoning steps, leading to divergent reasoning paths and unstable outcomes. To address this issue, we propose EBM-CoT, an Energy-Based Chain-of-Thought Calibration framework that refines latent thought representations through an energy-based model (EBM). Our method dynamically adjusts latent reasoning trajectories toward lower-energy, high-consistency regions in the embedding space, improving both reasoning accuracy and consistency without modifying the base language model. Extensive experiments across mathematical, commonsense, and symbolic reasoning benchmarks demonstrate that the proposed framework significantly enhances the consistency and efficiency of multi-step reasoning in LLMs.
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。
