Privacy management for conversational AI agents is reframed as a dynamic alignment problem in which agents learn a user's latent privacy-utility reward function from feedback.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences
Privacy management for conversational AI agents is reframed as a dynamic alignment problem in which agents learn a user's latent privacy-utility reward function from feedback.