arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01714cs.LG
收藏

作为类比推理器的大语言模型

Large Language Models as Analogical Reasoners

Google DeepMind(谷歌DeepMind);Stanford University(斯坦福大学)

Michihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat, Jure Leskovec, Percy Liang, Ed H. Chi, Denny Zhou

AI总结:

本研究提出类比提示方法,让大语言模型自行生成相关示例知识再推理,无需标注或检索示例,在多类推理任务上性能优于0-shot和手动少样本思维链提示。

摘要:

面向语言模型的思维链(Chain-of-thought, CoT)提示在各类推理任务中展现了出色的性能,但通常需要带有标注的推理过程示例。在本研究中,我们提出了一种新的提示方法——类比提示(analogical prompting),旨在自动引导大语言模型的推理过程。该方法受类比推理这一人类借助相关过往经验解决新问题的认知过程启发,会提示语言模型在着手解决给定问题前,自行生成上下文中的相关示例或知识。该方法具备多项优势:无需对示例进行标注或检索,具备通用性与便捷性;还能针对每个问题定制生成的示例与知识,具备适应性。实验结果表明,该方法在多种推理任务上的表现优于0-shot CoT和手动少样本CoT,涵盖GSM8K与MATH数据集的数学解题、Codeforces的代码生成,以及BIG-Bench中的其他推理任务。

英文摘要:

Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks, but typically needs labeled exemplars of the reasoning process. In this work, we introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models. Inspired by analogical reasoning, a cognitive process in which humans draw from relevant past experiences to tackle new problems, our approach prompts language models to self-generate relevant exemplars or knowledge in the context, before proceeding to solve the given problem. This method presents several advantages: it obviates the need for labeling or retrieving exemplars, offering generality and convenience; it can also tailor the generated exemplars and knowledge to each problem, offering adaptability. Experimental results show that our approach outperforms 0-shot CoT and manual few-shot CoT in a variety of reasoning tasks, including math problem solving in GSM8K and MATH, code generation in Codeforces, and other reasoning tasks in BIG-Bench.

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。

↑