不训练模型，用人类方法论引导推理，提升复杂任务表现
Chain of Methodologies: Scaling Test Time Computation without Training
- 引入人类方法论作为提示框架，激活模型系统性推理能力
- 无需微调，在多个复杂任务上超越现有基线方法
- 适合需要可解释推理的场景，如科研、法律分析
大型语言模型（LLMs）在处理复杂推理任务时常因训练数据中缺乏深入洞察而受限，而这些洞察通常不在公开文档中。本文提出链式方法论（Chain of Methodologies, CoM），一种创新且直观的提示框架，通过整合人类的方法论知识，增强模型的结构化思维能力，使其能在不进行显式微调的情况下完成复杂任务。CoM利用先进LLM的元认知能力，通过用户定义的方法论激活系统性推理过程。实验表明，CoM在多项复杂任务上优于现有基线方法，展示了无需训练的提示方法在复杂推理中的鲁棒性，为实现类人级推理提供了新路径。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data, which are typically absent in publicly available documents. This paper introduces the Chain of Methodologies (CoM), an innovative and intuitive prompting framework that enhances structured thinking by integrating human methodological insights, enabling LLMs to tackle complex tasks with extended reasoning. CoM leverages the metacognitive abilities of advanced LLMs, activating systematic reasoning throught user-defined methodologies without explicit fine-tuning. Experiments show that CoM surpasses competitive baselines, demonstrating the potential of training-free prompting methods as robust solutions for complex reasoning tasks and bridging the gap toward human-level reasoning through human-like methodological insights.
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。