作者位次 #3/4ACL 2026Poster· Natural Language Processing
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
Kyomin Hwang · Hyeonjin Kim · Sangyeon Cho · NOJUN KWAK
摘要
While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII). For LLMs trained on multilingual corpora, Multilingual Machine Unlearning (MMU) aims to remove information across multiple languages. However, p...