paper-with-me

Papers

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

2024-02-02 · Jiajie Zhang, Shulin Cao, Linmei Hu, Ling Feng, Lei Hou, Juanzi Li

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.

📄 PDF Abstract BibTeX arXiv:2402.01619

Code (1)

thu-keg/kb-plugin 공식 구현 pytorch

Tasks

Program inductionSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules

2023-10-24 · Chaojun Xiao, Yuqi Luo, Wenbin Zhang, Pengle Zhang 외

Pre-trained language models (PLMs) have achieved remarkable results on NLP tasks but at the expense of huge parameter sizes and the consequent computational costs. In this paper, we propose Variator, a parameter-efficien…

Computational Efficiency

Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks

2024-03-01 · CVPR 2024 1 · Yuhao Liu, Zhanghan Ke, Fang Liu, Nanxuan Zhao 외

Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle with handling diverse low-level tasks th…

Image Generation

Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins

2025-12-03 · Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen 외 arxiv

Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past knowledge in a shared single-model framew…

Continual Learning

On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces

2026-08-28 · Ahmed Hereiz, Yingzhe Lyu, Hao Li, Bram Adams 외 arxiv

AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly extended through plugin marketplaces, yet the structure, maintenance, and co-evolution dynamics of these e…

Plug-and-Play Knowledge Injection for Pre-trained Language Models

2023-05-28 · Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang 외

Injecting external knowledge can improve the performance of pre-trained language models (PLMs) on various downstream NLP tasks. However, massive retraining is required to deploy new knowledge injection methods or knowled…