MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
MiCRo is introduced, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations and effectively captures diverse human preferences and significantly improves downstream personalization.
Jingyan Shen, Jiarui Yao, Rui Yang et al.
· Conference on Empirical Meth... · 11 citations
· ⚡3