AI RESEARCH

Say Something Else: Rethinking Contextual Privacy as Information Sufficiency

arXiv CS.CL

ArXi:2604.06409v1 Announce Type: cross LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems only suppression (omitting sensitive information) and generalization (replacing information with an abstraction), and are typically evaluated on single isolated messages, leaving both the strategy space and evaluation setting incomplete. We formalize privacy-preserving LLM communication as an \textbf{Information Sufficiency (IS)} task.