ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
This addresses the problem of enhancing reasoning accuracy in LLMs for tasks with implicit entity relationships, representing an incremental improvement over existing CoT methods.
The paper tackles the challenge of LLMs struggling with complex scenarios involving multiple entities by proposing ERA-CoT, a method that improves Chain-of-Thought reasoning through entity relationship analysis, resulting in an average 5.1% performance improvement on GPT-3.5 compared to previous SOTA baselines.
Large language models (LLMs) have achieved commendable accomplishments in various natural language processing tasks. However, LLMs still encounter significant challenges when dealing with complex scenarios involving multiple entities. These challenges arise from the presence of implicit relationships that demand multi-step reasoning. In this paper, we propose a novel approach ERA-CoT, which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chain-of-Thoughts (CoT). Experimental results show that ERA-CoT demonstrates the superior performance of our proposed method compared to current CoT prompting methods, achieving a significant improvement of an average of 5.1\% on GPT3.5 compared to previous SOTA baselines. Our analysis indicates that ERA-CoT increases the LLM's understanding of entity relationships, significantly improves the accuracy of question answering, and enhances the reasoning ability of LLMs.