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

TL;DR

KB-Plugin is a flexible framework that enables large language models to induce programs over low-resourced knowledge bases by using self-supervised schema encoding and transfer learning from rich-resourced KBs.

Contribution

It introduces a plug-and-play schema encoding module and a transfer learning approach for program induction over low-resourced KBs, reducing data requirements.

Findings

Achieves comparable performance with 25x smaller LLMs.

Outperforms existing methods on low-resourced KBQA datasets.

Approaches supervised method performance.

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 the 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 this information to induce programs over this KB. Experiments on five heterogeneous KBQA datasets show that KB-Plugin achieves better or comparable performance with 25$\times$ smaller backbone LLM compared to SoTA PI methods for low-resourced KBs, and even approaches the performance of supervised methods. Our code and data are available at https://github.com/THU-KEG/KB-Plugin.