KB-Plugin：一种面向大语言模型的即插即用框架，用于在低资源知识库上归纳程序
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases
AI总结：
针对低资源知识库缺乏标注数据导致大语言模型程序归纳困难的问题，提出即插即用框架KB-Plugin，通过模式插件和PI插件实现低资源KB上的程序归纳，在小25倍骨干模型下性能优于或持平现有最优方法，接近监督方法水平。
摘要：
程序归纳（PI）已成为利用知识库（KB）辅助大语言模型（LLM）回答复杂知识密集型问题的一种颇具前景的范式。然而，PI通常依赖大量平行的问题-程序对来让LLM了解给定KB的模式，因此对于许多缺乏标注数据的低资源KB而言颇具挑战。为此，我们提出KB-Plugin，这是一种即插即用框架，能让LLM在任意低资源KB上归纳程序。首先，KB-Plugin采用自监督学习，将给定KB的详细模式信息编码到一个可插拔模块中，即模式插件（schema plugin）。其次，KB-Plugin利用来自高资源KB的丰富标注数据训练另一个可插拔模块，即PI插件（PI plugin），该模块可帮助LLM从任意KB的模式插件中提取与问题相关的模式信息，并利用这些信息在该KB上归纳程序。在五个异构KBQA数据集上的实验表明，与面向低资源KB的现有最优（SoTA）PI方法相比，KB-Plugin在骨干LLM规模小25倍的情况下取得了更优或相当的性能，甚至接近监督方法的性能。我们的代码和数据可在https://github.com/THU-KEG/KB-Plugin 获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
