Presents a clinically grounded privacy evaluation framework for medical LMs that measures verbatim memorization and semantic leakage of diagnoses across tiers of adversarial access, finding high leakage from routine metadata on a model trained on 378k notes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Clinically Grounded Privacy Evaluation of Medical LMs
Presents a clinically grounded privacy evaluation framework for medical LMs that measures verbatim memorization and semantic leakage of diagnoses across tiers of adversarial access, finding high leakage from routine metadata on a model trained on 378k notes.