A dynamic relational unlearning framework and benchmark show that document MLLMs jointly leak correlated private fields under weak visual evidence, and that the framework lowers the leakage rate while partly preserving extraction utility.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs
A dynamic relational unlearning framework and benchmark show that document MLLMs jointly leak correlated private fields under weak visual evidence, and that the framework lowers the leakage rate while partly preserving extraction utility.