AutoReason: Automatic Few-Shot Reasoning Decomposition

TL;DR

AutoReason introduces an automated approach to generate reasoning rationales for large language models, enhancing multi-step reasoning and interpretability without manual prompt crafting, demonstrated on Q extendash{}A datasets.

Contribution

It presents a novel system that automatically decomposes implicit queries into explicit questions to improve reasoning in LLMs, reducing reliance on hand-crafted prompts.

Findings

Increased accuracy on StrategyQA and HotpotQA datasets

Enhanced interpretability of reasoning process

Improved reasoning capabilities in weaker LLMs

Abstract

Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no capability to adjust itself to different queries. In this work, we propose a system to automatically generate rationales using CoT. Our method improves multi-step implicit reasoning capabilities by decomposing the implicit query into several explicit questions. This provides interpretability for the model, improving reasoning in weaker LLMs. We test our approach with two Q\&A datasets: StrategyQA and HotpotQA. We show an increase in accuracy with both, especially on StrategyQA. To facilitate further research in this field, the complete source code for this study has been made publicly available on GitHub: https://github.com/miralab-ai/autoreason.