Zero-Shot Chain-of-Thought Reasoning Guided by Swarm Intelligence Algorithms in Large Language Models

ACL ARR 2024 June Submission784 Authors

Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving nature of sentence prefixes during the pre-training phase, existing zero-shot CoT prompting methods that employ identical CoT prompting across all task instances may not be optimal. In this paper, we introduce a novel zero-shot prompting method that leverages swarm intelligence algorithms to dynamically generate diverse promptings for LLMs. Our approach involves initializing several CoT promptings, performing evolutionary operations based on LLMs to create a varied set, and utilizing the LLMs to select a suitable CoT prompting for a given problem. Additionally, a rewriting operation, guided by the selected CoT prompting, enhances the understanding of the LLMs about the problem. Extensive experiments conducted across ten reasoning datasets demonstrate the superior performance of our proposed method compared to current zero-shot CoT prompting methods on both black-box and open-source LLMs. Moreover, in-depth analytical experiments underscore the adaptability and effectiveness of our method in various reasoning tasks.

Paper Type: Long

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: Chain-of- thought reasoning , zero-shot, large language models

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English

Submission Number: 784