AutoReason: Automatic Few-Shot Reasoning Decomposition
This addresses the need for more adaptable and interpretable reasoning methods in AI, particularly for weaker LLMs, though it is incremental as it builds on existing CoT techniques.
The paper tackles the problem of limited applicability of Chain of Thought (CoT) in large language models by proposing a system to automatically generate rationales, improving multi-step implicit reasoning capabilities. It shows an increase in accuracy on StrategyQA and HotpotQA datasets, especially on StrategyQA.
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.