LENS: localized updates facilitate patient-level unlearning in clinical large language models
Year: 2026
Type: article
Abstract: Large language models fine-tuned on clinical records can reproduce patient information that a patient may ask to have removed. A deletion request applies only to the patient who made it, so outputs for other patients in the same fine-tuning data should remain unchanged. Unlearning studies typically check general medical knowledge but rarely examine these non-deleted patients. Restricting updates to a subset of model components has been reported to reduce side effects on untargeted knowledge, but its effect on non-deleted patients remains unclear. We propose layer-wise evidence-based neural suppression (LENS), which confines the unlearning update to a single four-layer window of the fine-tuning adapter. We fine-tuned MedGemma-4B-IT on MIMIC-III notes with synthetic patient names. After fine-tuning, ROUGE-L on deleted and non-deleted patients was 0.98–0.99, and a reference model trained without the deleted patients scored 0.33 on them. Existing methods that brought the deleted patients to this level (0.29–0.39) lowered the non-deleted patients to 0.47–0.69. LENS brought the deleted patients to 0.34 and kept the non-deleted patients at 0.90. External medical benchmark accuracy changed by less than 0.02 for every method and did not distinguish these outcomes. These results suggest that unlearning should also be evaluated on the non-deleted patients.
Source: Scientific Reports
Institutions: Yonsei University, Asan Medical Center, University of Ulsan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7237364200
FWCI:
Cites:
Cited by:
Related to:
