9 papers
Context-Aware Disentanglement for Cross-Domain Sequential Recommendation: A Causal View
Xingzi Wang, Qingtian Bian, Hui Fang
Cross-Domain Sequential Recommendation (CDSR) aims to en-hance recommendation quality by transferring knowledge across domains, offering effective solutions to data sparsity and co…
A Reinforcement Learning Method to Factual and Counterfactual Explanations for Session-based Recommendation
Han Zhou, Hui Fang, Zhu Sun +1
Session-based Recommendation (SR) systems have recently achieved considerable success, yet their complex, "black box" nature often obscures why certain recommendations are made. Ex…
ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
Dayu Yang, Hui Fang
Connecting conversation with external domain knowledge is vital for conversational recommender systems (CRS) to correctly understand user preferences. However, existing solutions e…
Research on Conversational Recommender System Considering Consumer Types
Yaying Luo, Hui Fang, Zhu Sun
Conversational Recommender Systems (CRS) provide personalized services through multi-turn interactions, yet most existing methods overlook users' heterogeneous decision-making styl…
Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation
Kaidong Feng, Zhu Sun, Hui Fang +3
Large Language Models (LLMs) have shown potential in automatic bundle generation but suffer from prohibitive computational costs. Although knowledge distillation offers a pathway t…
PreQRAG -- Classify and Rewrite for Enhanced RAG
Damian Martinez, Catalina Riano, Hui Fang
This paper presents the submission of the UDInfo team to the SIGIR 2025 LiveRAG Challenge. We introduce PreQRAG, a Retrieval Augmented Generation (RAG) architecture designed to imp…