Skip to yearly menu bar Skip to main content


Poster

Large Language Models as Analogical Reasoners

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

Halle B #129
[ ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract:

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.

Chat is not available.