Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.12029 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913856951943168 |
|---|---|
| author | Zhao, Qi Yang, Hongyu Song, Qi Yao, Xinwei Li, Xiangyang |
| author_facet | Zhao, Qi Yang, Hongyu Song, Qi Yao, Xinwei Li, Xiangyang |
| contents | Large language models (LLMs) have demonstrated remarkable capabilities in various complex tasks, yet they still suffer from hallucinations. By incorporating and exploring external knowledge, such as knowledge graphs(KGs), LLM's ability to provide factual answers has been enhanced. This approach carries significant practical implications. However, existing methods suffer from three key limitations: insufficient mining of LLMs' internal knowledge, constrained generation of interpretable reasoning paths, and unclear fusion of internal and external knowledge. Therefore, we propose KnowPath, a knowledge-enhanced large model framework driven by the collaboration of internal and external knowledge. It relies on the internal knowledge of the LLM to guide the exploration of interpretable directed subgraphs in external knowledge graphs, better integrating the two knowledge sources for more accurate reasoning. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of KnowPath. Our code and data are available at https://github.com/tize-72/KnowPath. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12029 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs Zhao, Qi Yang, Hongyu Song, Qi Yao, Xinwei Li, Xiangyang Artificial Intelligence Large language models (LLMs) have demonstrated remarkable capabilities in various complex tasks, yet they still suffer from hallucinations. By incorporating and exploring external knowledge, such as knowledge graphs(KGs), LLM's ability to provide factual answers has been enhanced. This approach carries significant practical implications. However, existing methods suffer from three key limitations: insufficient mining of LLMs' internal knowledge, constrained generation of interpretable reasoning paths, and unclear fusion of internal and external knowledge. Therefore, we propose KnowPath, a knowledge-enhanced large model framework driven by the collaboration of internal and external knowledge. It relies on the internal knowledge of the LLM to guide the exploration of interpretable directed subgraphs in external knowledge graphs, better integrating the two knowledge sources for more accurate reasoning. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of KnowPath. Our code and data are available at https://github.com/tize-72/KnowPath. |
| title | KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2502.12029 |