Hypotheses-Guided Self Distillation for Continual Personalization
HypReflect is introduced, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation.
Eunjeong Hwang, Kushan Mitra, Dan Zhang et al.
· 1 citation