TY  - CONF

T1  - PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

JO  - Findings of the Association for Computational Linguistics: EACL 2026

UR  - https://doi.org/10.18653/v1/2026.findings-eacl.271

PY  - 2026/01/01

AU  - Hughes A

AU  - Duddu V

AU  - Asokan N

AU  - Aletras N

AU  - Ma N

ED  - 

DO  - DOI: 10.18653/v1/2026.findings-eacl.271

PB  - Association for Computational Linguistics

SP  - 5139

EP  - 5153

Y2  - 2026/04/22

ER  -