5 papers
Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework
Nipun B Nair, Tongtong Wu, Weiqing Wang
Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify…
Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval
Tuan-Luc Huynh, Weiqing Wang, Trung Le +4
Retrievers are a key bottleneck in Temporal Retrieval-Augmented Generation (RAG) systems: failing to retrieve temporally relevant context can degrade downstream generation, regardl…
MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +5
Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resou…
PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +5
Differentiable Search Index (DSI) utilizes pre-trained language models to perform indexing and document retrieval via end-to-end learning without relying on external indexes. Howev…
Scalable and Effective Negative Sample Generation for Hyperedge Prediction
Shilin Qu, Weiqing Wang, Yuan-Fang Li +2
Hyperedge prediction is crucial in hypergraph analysis for understanding complex multi-entity interactions in various web-based applications, including social networks and e-commer…