东华大学学报（英文版）2026，Vol.43Issue(1)：91-103,13.DOI:10.19884/j.1672-5220.202408003
LLMKB:基于知识库增强的大语言模型对话式推荐
LLMKB:Large Language Models with Knowledge Base Augmentation for Conversational Recommendation
方秀 1邱斯嘉 1孙国豪 1陆金虎1
作者信息
- 1. 东华大学 计算机科学与技术学院,上海 201620
- 折叠
摘要
Abstract
Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstanding performance across various domains,thereby prompting researchers to investigate their applicability in recommendation systems.However,due to the lack of task-specific knowledge and an inefficient feature extraction process,LLMs still have suboptimal performance in recommendation tasks.Therefore,external knowledge sources,such as knowledge graphs(KGs)and knowledge bases(KBs),are often introduced to address the issue of data sparsity.Compared to KGs,KBs possess higher retrieval efficiency,making them more suitable for scenarios where LLMs serve as recommenders.To this end,we introduce a novel framework integrating LLMs with KBs for enhanced retrieval generation,namely LLMKB.LLMKB initially leverages structured knowledge to create mapping dictionaries,extracting entity-relation information from heterogeneous knowledge to construct KBs.Then,LLMKB achieves the embedding calibration between user information representations and documents in KBs through retrieval model fine-tuning.Finally,LLMKB employs retrieval-augmented generation to produce recommendations based on fused text inputs,followed by post-processing.Experiment results on two public CRS datasets demonstrate the effectiveness of our framework.Our code is publicly available at the link:https://anonymous.4open.science/r/LLMKB-6FD0.关键词
推荐系统/大语言模型(LLM)/知识库(KB)Key words
recommender system/large language model(LLM)/knowledge base(KB)分类
信息技术与安全科学引用本文复制引用
方秀,邱斯嘉,孙国豪,陆金虎..LLMKB:基于知识库增强的大语言模型对话式推荐[J].东华大学学报（英文版）,2026,43(1):91-103,13.
