Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models

/in /by

Publication Date: 7/31/2024

Event: https://arxiv.org

Reference: https://arxiv.org/abs/2410.08436

Authors: Zi’ou Zheng, Queen’s University; Christopher Malon, NEC Laboratories America, Inc.; Martin Renqiang Min, NEC Laboratories America, Inc.; Xiaodan Zhu, Queen’s University

Abstract: When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving models’ explainability. This paper is centered around a focused study: whether the current state-of-the-art generalist LLMs can leverage the structures in a few examples to better construct the proof structures with textit (Unknown sysvar: (in-context learning)). Our study specifically focuses on structure-aware demonstration and structure-aware pruning. We demonstrate that they both help improve performance. A detailed analysis is provided to help understand the results.

Publication Link: https://arxiv.org/abs/2410.08436