5 papers
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
Mingxi Zou, Jiaxiang Chen, Junfan Li +4
Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systemati…
MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions
Yuantong Li, Lei Yuan, Zhihao Zheng +27
Modern recommendation systems rank candidates by aggregating multiple behavioral signals through a value model. However, many commonly used signals are inherently affected by heter…
Verifiable Reasoning for LLM-based Generative Recommendation
Xinyu Lin, Hanqing Zeng, Hanchao Yu +8
Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation through deep understanding of complex user preference. Existing…
Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System
Jiang Zhang, Yubo Wang, Wei Chang +14
Approximate nearest neighbor (ANN) search is widely used in the retrieval stage of large-scale recommendation systems. In this stage, candidate items are indexed using their learne…
Balancing Semantic Relevance and Engagement in Related Video Recommendations
Amit Jaspal, Feng Zhang, Wei Chang +5
Related video recommendations commonly use collaborative filtering (CF) driven by co-engagement signals, often resulting in recommendations lacking semantic coherence and exhibitin…