Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.09957 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910794003775488 |
|---|---|
| author | Gao, Zengyi Cao, Yukun Wang, Hairu Ke, Ao Feng, Yuan Xie, Xike Zhou, S Kevin |
| author_facet | Gao, Zengyi Cao, Yukun Wang, Hairu Ke, Ao Feng, Yuan Xie, Xike Zhou, S Kevin |
| contents | To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as external resource to enhance LLMs reasoning. However, existing KG-RAG approaches struggle with a trade-off between flexibility and retrieval quality. Modular methods prioritize flexibility by avoiding the use of KG-fine-tuned models during retrieval, leading to fixed retrieval strategies and suboptimal retrieval quality. Conversely, coupled methods embed KG information within models to improve retrieval quality, but at the expense of flexibility. In this paper, we propose a novel flexible modular KG-RAG framework, termed FRAG, which synergizes the advantages of both approaches. FRAG estimates the hop range of reasoning paths based solely on the query and classify it as either simple or complex. To match the complexity of the query, tailored pipelines are applied to ensure efficient and accurate reasoning path retrieval, thus fostering the final reasoning process. By using the query text instead of the KG to infer the structural information of reasoning paths and employing adaptable retrieval strategies, FRAG improves retrieval quality while maintaining flexibility. Moreover, FRAG does not require extra LLMs fine-tuning or calls, significantly boosting efficiency and conserving resources. Extensive experiments show that FRAG achieves state-of-the-art performance with high efficiency and low resource consumption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09957 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs Gao, Zengyi Cao, Yukun Wang, Hairu Ke, Ao Feng, Yuan Xie, Xike Zhou, S Kevin Computation and Language To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as external resource to enhance LLMs reasoning. However, existing KG-RAG approaches struggle with a trade-off between flexibility and retrieval quality. Modular methods prioritize flexibility by avoiding the use of KG-fine-tuned models during retrieval, leading to fixed retrieval strategies and suboptimal retrieval quality. Conversely, coupled methods embed KG information within models to improve retrieval quality, but at the expense of flexibility. In this paper, we propose a novel flexible modular KG-RAG framework, termed FRAG, which synergizes the advantages of both approaches. FRAG estimates the hop range of reasoning paths based solely on the query and classify it as either simple or complex. To match the complexity of the query, tailored pipelines are applied to ensure efficient and accurate reasoning path retrieval, thus fostering the final reasoning process. By using the query text instead of the KG to infer the structural information of reasoning paths and employing adaptable retrieval strategies, FRAG improves retrieval quality while maintaining flexibility. Moreover, FRAG does not require extra LLMs fine-tuning or calls, significantly boosting efficiency and conserving resources. Extensive experiments show that FRAG achieves state-of-the-art performance with high efficiency and low resource consumption. |
| title | FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.09957 |