ChainLM：通过改进的思维链提示赋能大型语言模型
ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
AI总结：
本文提出CoTGenius框架自动生成高质量思维链提示，并构建数据集微调Llama 2-Chat模型得到ChainLM，同时提出步级辩论方法解决推理累积误差，显著提升了模型复杂推理能力。
摘要：
思维链（CoT）提示能够增强大型语言模型（LLMs）的推理能力，已成为解决复杂推理任务的主要方法。现有的CoT合成方法通常专注于较简单的推理任务，因此导致CoT提示质量低下且不一致。为应对这一挑战，我们对CoT提示进行了实证研究，并提出了CoTGenius，这是一个旨在自动生成高质量CoT提示的新框架。CoTGenius基于三大进化策略（即复杂化、多样化和具体化）以及两种过滤机制（进化成功判断和正确性验证）开发。我们进一步利用CoTGenius创建了大规模的CoT数据集，随后在该数据集上对Llama 2-Chat 7B和13B模型进行微调。我们将最终模型称为ChainLM。为解决推理步骤中的累积误差问题，我们提出了一种步级辩论方法，其中多个辩论者讨论每个推理步骤以得出正确答案。大量实验表明，与现有模型相比，我们的ChainLM模型在处理一系列复杂推理问题方面表现出更强的能力。此外，我们还深入分析了CoTGenius中数据类别对模型性能的影响。我们在 https://github.com/RUCAIBox/ChainLM 发布了数据集和代码。
英文摘要：
Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usually focus on simpler reasoning tasks and thus result in low-quality and inconsistent CoT prompts. In response to this challenge, we present an empirical investigation of CoT prompting and introduce CoTGenius, a novel framework designed for the automatic generation of superior CoT prompts. CoTGenius is developed based on three major evolution strategies, i.e., complicate, diversify, and specify-alongside two filtering mechanisms: evolutionary success judgement and correctness verification. We further employ CoTGenius to create an extensive CoT dataset, and subsequently fine-tune the Llama 2-Chat 7B and 13B models on this dataset. We call the resulting model ChainLM. To deal with the cumulative error issue in reasoning steps, we propose a step-level debating method, wherein multiple debaters discuss each reasoning step to arrive at the correct answer. Extensive experiments demonstrate that our ChainLM models exhibit enhanced proficiency in addressing a spectrum of complex reasoning problems compared to existing models. In addition, we conduct an in-depth analysis of the impact of data categories within CoTGenius on the model performance. We release our dataset and code at https://github.com/RUCAIBox/ChainLM.
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。
