CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Nay Myat Min, Long H. Pham, Yige Li, Jun Sun 0001. CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net, 2025. [doi]

This author has not been identified. Look up 'Nay Myat Min' in GoogleThis author has not been identified. Look up 'Long H. Pham' in GoogleThis author has not been identified. Look up 'Yige Li' in GoogleThis author has not been identified. Look up 'Jun Sun 0001' in Google

runs on WebDSL