从自训练视角重新思考思维链
Rethinking Chain-of-Thought from the Perspective of Self-Training
AI总结：
本文从自训练视角重新审视思维链，提出一种整合任务特定提示模块与自适应推理迭代模块的新框架，以降低预测不确定性并解决过度推理问题，在性能和效率上均获显著提升。
摘要：
思维链（Chain-of-Thought, CoT）推理已成为激活大型语言模型（LLMs）潜在能力的有效方法。有趣的是，我们观察到思维链推理和自训练共享核心目标：迭代地利用模型生成的信息来逐步降低预测不确定性。基于这一见解，我们提出了一种新颖的思维链框架以提高推理性能。我们的框架整合了两个关键组件：（i）一个任务特定的提示模块，用于优化初始推理过程；（ii）一个自适应推理迭代模块，动态细化推理过程并解决先前思维链方法的局限性，即过度推理和连续推理迭代之间的高相似性。大量实验表明，所提出的方法在性能和计算效率方面均取得了显著优势。
英文摘要：
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging model-generated information to progressively reduce prediction uncertainty. Building on this insight, we propose a novel CoT framework to improve reasoning performance. Our framework integrates two key components: (i) a task-specific prompt module that optimizes the initial reasoning process, and (ii) an adaptive reasoning iteration module that dynamically refines the reasoning process and addresses the limitations of previous CoT approaches, \ie over-reasoning and high similarity between consecutive reasoning iterations. Extensive experiments demonstrate that the proposed method achieves significant advantages in both performance and computational efficiency.
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。
