Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?

TL;DR

This paper investigates whether large language models can perform true analogical reasoning by comparing the effectiveness of relevant versus random self-generated examples, revealing that random examples can sometimes outperform relevant ones.

Contribution

The study systematically explores LLMs' ability for analogical reasoning, demonstrating that self-generated random examples can be as effective or better than relevant ones, and introduces methods to improve performance and reduce costs.

Findings

Random self-generated examples can outperform relevant ones in some tasks.

Accuracy of self-generated examples is crucial for model performance.

Proposed methods improve accuracy and reduce inference costs.

Abstract

Analogical reasoning is a unique ability of humans to address unfamiliar challenges by transferring strategies from relevant past experiences. One key finding in psychology is that compared with irrelevant past experiences, recalling relevant ones can help humans better handle new tasks. Coincidentally, the NLP community has also recently found that self-generating relevant examples in the context can help large language models (LLMs) better solve a given problem than hand-crafted prompts. However, it is yet not clear whether relevance is the key factor eliciting such capability, i.e., can LLMs benefit more from self-generated relevant examples than irrelevant ones? In this work, we systematically explore whether LLMs can truly perform analogical reasoning on a diverse set of reasoning tasks. With extensive experiments and analysis, we show that self-generated random examples can surprisingly achieve comparable or even better performance on certain tasks, e.g., 4% performance boost on GSM8K with random biological examples. We find that the accuracy of self-generated examples is the key factor and subsequently design two novel methods with improved performance and significantly reduced inference costs. Overall, we aim to advance a deeper understanding of LLM analogical reasoning and hope this work stimulates further research in the design of self-generated contexts.