Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering

Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Xu Jia, Min Zhang


Abstract
Despite Large Language Models (LLMs) have performed impressively in various Natural Language Processing (NLP) tasks, their inherent hallucination phenomena severely challenge their credibility in complex reasoning. Combining explainable Knowledge Graphs (KGs) with LLMs is a promising path to address this issue. However, structured KGs are difficult to utilize, and how to make LLMs understand and incorporate them is a challenging topic. We thereby reorganize a more efficient structure of KGs, while designing the KG-related instruction tuning and continual pre-training strategies to enable LLMs to learn and internalize this form of representation effectively. Moreover, we construct subgraphs to further enhance the retrieval capabilities of KGs via CoT reasoning. Extensive experiments on two KGQA datasets demonstrate that our model achieves convincing performance compared to strong baselines.
Anthology ID:
2024.findings-emnlp.446
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7598–7610
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.446
DOI:
Bibkey:
Cite (ACL):
Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Xu Jia, and Min Zhang. 2024. Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7598–7610, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering (Ji et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.446.pdf