arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.12147cs.CLcs.AI

LogiCoT:逻辑思维链指令微调

LogiCoT: Logical Chain-of-Thought Instruction-Tuning

Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Tencent AI lab(腾讯AI实验室);Alibaba Group(阿里巴巴集团);Westlake University(西湖大学)

Hanmeng Liu, Zhiyang Teng, Leyang Cui, Chaoli Zhang, Qiji Zhou, Yue Zhang

AI总结:

本文提出LogiCoT数据集,通过收集指令引导GPT-4生成逻辑思维链推理依据,用于指令微调以提升模型在复杂推理任务上的能力,弥补现有自指令微调方法在逻辑推理方面的不足。

摘要:

生成式预训练Transformer 4(GPT-4)展示了令人印象深刻的思维链推理能力。近期关于自指令微调的工作,如Alpaca,侧重于提升模型的通用能力。这些指令使模型在开放域文本生成和改写等通用任务上达到与GPT-3.5相当的性能。然而,它们在帮助模型处理复杂推理任务方面仍存在不足。为弥合这一差距,本文提出了LogiCoT,一个基于GPT-4的逻辑思维链推理新指令微调数据集。我们详细阐述了收集指令以提示GPT-4生成思维链推理依据的过程。LogiCoT作为一套用于教授模型逻辑推理的指令集,能够激发通用推理技能。

英文摘要:

Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models. These instructions enable the model to achieve performance comparable to GPT-3.5 on general tasks like open-domain text generation and paraphrasing. However, they fall short of helping the model handle complex reasoning tasks. To bridge the gap, this paper presents LogiCoT, a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4. We elaborate on the process of harvesting instructions for prompting GPT-4 to generate chain-of-thought rationales. LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.

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。

↑