A hybrid system that filters sensitive purchases out of LLM-based recommendation prompts and generates those recommendations locally nearly matches full-data recommendation quality while keeping most sensitive data off the server.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Preserving Privacy and Utility in LLM-Based Product Recommendations
A hybrid system that filters sensitive purchases out of LLM-based recommendation prompts and generates those recommendations locally nearly matches full-data recommendation quality while keeping most sensitive data off the server.