ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911907445735424 |
|---|---|
| author | Liu, Yanming Peng, Xinyue Du, Tianyu Yin, Jianwei Liu, Weihao Zhang, Xuhong |
| author_facet | Liu, Yanming Peng, Xinyue Du, Tianyu Yin, Jianwei Liu, Weihao Zhang, Xuhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06932 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis Liu, Yanming Peng, Xinyue Du, Tianyu Yin, Jianwei Liu, Weihao Zhang, Xuhong Computation and Language 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. |
| title | ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.06932 |