Large language models make sample-efficient recommender systems  

作　　者：Jianghao LIN Xinyi DAI Rong SHAN Bo CHEN Ruiming TANG Yong YU Weinan ZHANG 

机构地区：[1]Computer Science and Technology,Shanghai Jiao Tong University,Shanghai 200240,China [2]Huawei Noah’s Ark Lab,Shenzhen 518129,China

出　　处：《Frontiers of Computer Science》2025年第4期115-117,共3页计算机科学前沿(英文版)

基　　金：supported by the National Natural Science Foundation of China(Grant No.62177033).

摘　　要：1 Introduction Large language models(LLMs)have achieved remarkable progress in the field of natural language processing(NLP),showing impressive abilities to generate human-like texts for a broad range of tasks[1].Consequently,recent works start to investigate the application of LLMs in recommender systems.They adopt LLMs for various recommendation tasks,and show promising performance from different aspects(e.g.,user profiling).In this letter,we mainly focus on promoting the sample efficiency of recommender systems by involving large language models.

关 键 词：recommendation tasksand recommender systemsthey recommender systems large language models large language models llms recommender sy promoting sample efficiency natural language processing nlp showing 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]