6 papers
Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
Jiongran Wu, Jiahao Liu, Dongsheng Li +7
Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommenda…
LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
Shengkang Gu, Jiahao Liu, Dongsheng Li +7
Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies of…
Improving LLM-powered Recommendations with Personalized Information
Jiahao Liu, Xueshuo Yan, Dongsheng Li +6
Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline…
AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
Jiahao Liu, Shengkang Gu, Dongsheng Li +7
LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions…
Unbiased Collaborative Filtering with Fair Sampling
Jiahao Liu, Dongsheng Li, Hansu Gu +4
Recommender systems leverage extensive user interaction data to model preferences; however, directly modeling these data may introduce biases that disproportionately favor popular…
Oracle-guided Dynamic User Preference Modeling for Sequential Recommendation
Jiafeng Xia, Dongsheng Li, Hansu Gu +4
Sequential recommendation methods can capture dynamic user preferences from user historical interactions to achieve better performance. However, most existing methods only use past…