PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Anthony Hughes, Vasisht Duddu, N. Asokan, Nikolaos Aletras, Ning Ma 0002. PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing. In Vera Demberg, Kentaro Inui, Lluís Marquez, editors, Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 24-29, 2026. pages 5139-5153, Association for Computational Linguistics, 2026. [doi]

This author has not been identified. Look up 'Anthony Hughes' in GoogleThis author has not been identified. Look up 'Vasisht Duddu' in GoogleThis author has not been identified. Look up 'N. Asokan' in GoogleThis author has not been identified. Look up 'Nikolaos Aletras' in GoogleThis author has not been identified. Look up 'Ning Ma 0002' in Google

runs on WebDSL