作者位次 #2/7ACL 2026Findings· Findings of ACL
Representation-Guided Parameter-Efficient LLM Unlearning
Zeguan Xiao · Lang Mo · Yun Chen · Lei Yang · Jiehui Zhao · Lili Yang · Guanhua Chen
摘要
Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the forget-retain trade-off. This can be attributed to their reli...