safety security
The Retriever Gave the Outside Model Aliases
SEAG replaces sensitive entities before queries and documents reach an external generator, then restores the answer for the user.
Summary
SEAG replaces sensitive entities before queries and documents reach an external generator, then restores the answer for the user.
The proposed privacy layer detects confidential entities, generates aliases and applies the replacement table to both the user's query and retrieved documents before sending them to a third-party language model. The authors report more than 80 percent on their user-oriented correctness-and-concealment metric, while complete entity-hiding accuracy ranged from 74.91 to 77.83 percent across three tested models. Those residual misses mean the method is not a guarantee against disclosure.
Why it matters
SEAG replaces sensitive entities before queries and documents reach an external generator, then restores the answer for the user.
Limits and context
- Those residual misses mean the method is not a guarantee against disclosure.
Key claims
SEAG replaces sensitive entities before queries and documents reach an external generator, then restores the answer for the user.
Qualification: Those residual misses mean the method is not a guarantee against disclosure.
Evidence: source-2026-08-15-004
Sources
- arXiv preprint 2608.12675arXiv · primary research
Corrections
No corrections have been recorded for this story.