作者位次 #6/9ACL 2026Findings· Findings of ACL
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Xiaoyu Xu · Minxin Du · Zitong LI · Zi Liang · Zhibiao Guo · Zhang Shiyu · Peizhao Hu · Qingqing Ye · Haibo Hu
摘要
Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true “forgetting scope” learned by the model. We formalize two distinct unlearning granularities, domain-level and instance-level, an...