KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases

Jiajie Zhang, Shulin Cao, Linmei Hu, Ling Feng, Lei Hou, Juanzi Li


Abstract
Program induction (PI) has become a promising paradigm for using knowledge bases (KBs) to help large language models (LLMs) answer complex knowledge-intensive questions. Nonetheless, PI typically relies on a large number of parallel question-program pairs to make the LLM aware of the schema of a given KB, and is thus challenging for many low-resourced KBs that lack annotated data. To this end, we propose KB-Plugin, a plug-and-play framework that enables LLMs to induce programs over any low-resourced KB. Firstly, KB-Plugin adopts self-supervised learning to encode the detailed schema information of a given KB into a pluggable module, namely schema plugin. Secondly, KB-Plugin utilizes abundant annotated data from a rich-resourced KB to train another pluggable module, namely PI plugin, which can help the LLM extract question-relevant schema information from the schema plugin of any KB and utilize the information to induce programs over this KB. Experiments show that KB-Plugin outperforms SoTA low-resourced PI methods with 25x smaller backbone LLM on both large-scale and domain-specific KBs, and even approaches the performance of supervised methods.
Anthology ID:
2024.emnlp-main.168
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:
2868–2882
Language:
URL:
https://aclanthology.org/2024.emnlp-main.168/
DOI:
10.18653/v1/2024.emnlp-main.168
Bibkey:
Cite (ACL):
Jiajie Zhang, Shulin Cao, Linmei Hu, Ling Feng, Lei Hou, and Juanzi Li. 2024. KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 2868–2882, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases (Zhang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.168.pdf