[go: up one dir, main page]

CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering

Yike Wu, Yi Huang, Nan Hu, Yuncheng Hua, Guilin Qi, Jiaoyan Chen, Jeff Z. Pan


Abstract
Recent studies have explored the use of Large Language Models (LLMs) with Retrieval Augmented Generation (RAG) for Knowledge Graph Question Answering (KGQA). They typically require rewriting retrieved subgraphs into natural language formats comprehensible to LLMs. However, when tackling complex questions, the knowledge rewritten by existing methods may include irrelevant information, omit crucial details, or fail to align with the question’s semantics. To address them, we propose a novel rewriting method CoTKR, Chain- of-Thought Enhanced Knowledge Rewriting, for generating reasoning traces and corresponding knowledge in an interleaved manner, thereby mitigating the limitations of single-step knowledge rewriting. Additionally, to bridge the preference gap between the knowledge rewriter and the question answering (QA) model, we propose a training strategy PAQAF, Preference Alignment from Question Answering Feedback, for leveraging feedback from the QA model to further optimize the knowledge rewriter. We conduct experiments using various LLMs across several KGQA benchmarks. Experimental results demonstrate that, compared with previous knowledge rewriting methods, CoTKR generates the most beneficial knowledge representation for QA models, which significantly improves the performance of LLMs in KGQA.
Anthology ID:
2024.emnlp-main.205
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3501–3520
Language:
URL:
https://aclanthology.org/2024.emnlp-main.205
DOI:
Bibkey:
Cite (ACL):
Yike Wu, Yi Huang, Nan Hu, Yuncheng Hua, Guilin Qi, Jiaoyan Chen, and Jeff Z. Pan. 2024. CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3501–3520, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering (Wu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.205.pdf
Software:
 2024.emnlp-main.205.software.zip
Data:
 2024.emnlp-main.205.data.zip