Users of LLM chatbots hold incomplete, often mistaken mental models of memory features, yet actively trade privacy against personalization and demand granular control and transparency over how memories are stored, used, and inferred.
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
-
Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory
Users of LLM chatbots hold incomplete, often mistaken mental models of memory features, yet actively trade privacy against personalization and demand granular control and transparency over how memories are stored, used, and inferred.