ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909371004354560 |
|---|---|
| author | Luo, Haoran E, Haihong Tang, Zichen Peng, Shiyao Guo, Yikai Zhang, Wentai Ma, Chenghao Dong, Guanting Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh |
| author_facet | Luo, Haoran E, Haihong Tang, Zichen Peng, Shiyao Guo, Yikai Zhang, Wentai Ma, Chenghao Dong, Guanting Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh |
| contents | Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain: inefficient knowledge retrieval, mistakes of retrieval adversely impacting semantic parsing, and the complexity of previous KBQA methods. To tackle these challenges, we introduce ChatKBQA, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly. Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ. This work can also be regarded as a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering. Our code is publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08975 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models Luo, Haoran E, Haihong Tang, Zichen Peng, Shiyao Guo, Yikai Zhang, Wentai Ma, Chenghao Dong, Guanting Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh Computation and Language Artificial Intelligence Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain: inefficient knowledge retrieval, mistakes of retrieval adversely impacting semantic parsing, and the complexity of previous KBQA methods. To tackle these challenges, we introduce ChatKBQA, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly. Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ. This work can also be regarded as a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering. Our code is publicly available. |
| title | ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2310.08975 |