KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911116120031232 |
|---|---|
| author | Wang, Nan Fan, Yongqi zhu, yansha Wang, ZongYu Cao, Xuezhi He, Xinyan Jiang, Haiyun Ruan, Tong Liu, Jingping |
| author_facet | Wang, Nan Fan, Yongqi zhu, yansha Wang, ZongYu Cao, Xuezhi He, Xinyan Jiang, Haiyun Ruan, Tong Liu, Jingping |
| contents | Large Language Models (LLMs) face challenges in knowledge-intensive reasoning tasks like classic multi-hop question and answering, which involves reasoning across multiple facts. This difficulty arises because the chain of thoughts (CoTs) generated by LLMs in such tasks often deviate from real or a priori reasoning paths. In contrast, knowledge graphs (KGs) explicitly represent the logical connections between facts through entities and relationships. This reflects a significant gap. Meanwhile, large reasoning models (LRMs), such as o1, have demonstrated that long-step reasoning significantly enhances the performance of LLMs. Building on these insights, we propose KG-o1, a four-stage approach that integrates KGs to enhance the multi-hop reasoning abilities of LLMs. We first filter out initial entities and generate complex subgraphs. Secondly, we construct logical paths for subgraphs and then use knowledge graphs to build a dataset with a complex and extended brainstorming process, which trains LLMs to imitate long-term reasoning. Finally, we employ rejection sampling to generate a self-improving corpus for direct preference optimization (DPO), further refining the LLMs reasoning abilities. We conducted experiments on two simple and two complex datasets. The results show that KG-o1 models exhibit superior performance across all tasks compared to existing LRMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration Wang, Nan Fan, Yongqi zhu, yansha Wang, ZongYu Cao, Xuezhi He, Xinyan Jiang, Haiyun Ruan, Tong Liu, Jingping Computation and Language Artificial Intelligence Large Language Models (LLMs) face challenges in knowledge-intensive reasoning tasks like classic multi-hop question and answering, which involves reasoning across multiple facts. This difficulty arises because the chain of thoughts (CoTs) generated by LLMs in such tasks often deviate from real or a priori reasoning paths. In contrast, knowledge graphs (KGs) explicitly represent the logical connections between facts through entities and relationships. This reflects a significant gap. Meanwhile, large reasoning models (LRMs), such as o1, have demonstrated that long-step reasoning significantly enhances the performance of LLMs. Building on these insights, we propose KG-o1, a four-stage approach that integrates KGs to enhance the multi-hop reasoning abilities of LLMs. We first filter out initial entities and generate complex subgraphs. Secondly, we construct logical paths for subgraphs and then use knowledge graphs to build a dataset with a complex and extended brainstorming process, which trains LLMs to imitate long-term reasoning. Finally, we employ rejection sampling to generate a self-improving corpus for direct preference optimization (DPO), further refining the LLMs reasoning abilities. We conducted experiments on two simple and two complex datasets. The results show that KG-o1 models exhibit superior performance across all tasks compared to existing LRMs. |
| title | KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15790 |