InfoResearchPreprintLLM-specific
Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs
- Published
- Record updated
Summary
The authors argue that current prompt-privacy research is moving toward a single unified framework, which they say is misleading and can create a false sense of security because privacy depends on context. They contend that future work must confront tensions among desirable prompt-privacy properties, so attempts at a unified framework should be reconsidered.
Mitigation
They recommend three paths forward: application-specific deployment of LLMs, context-specific evaluation of privacy frameworks, and better privacy literacy.