Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models
This work addresses the problem of improving explainability and reasoning accuracy in LLMs for complex tasks, though it is incremental as it builds on existing in-context learning methods.
The paper investigated whether state-of-the-art large language models can use reasoning structures from examples to improve proof construction in multi-step natural language reasoning, finding that structure-aware demonstration and pruning techniques enhanced performance.
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 centred 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{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.