LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation 事件

LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation arXiv:2605.26612v1 Announce Type: new Abstract: Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization methods typically retrieve or summarize user histories in text, or compress them into static latent profiles and soft prompts. These approaches are efficient, but they treat a user's past behavior as an aggregate p