作者位次 #3/4ACL 2026Poster· Natural Language Processing
Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
Seunghee Koh · Sunghyun Baek · Youngdong Kim · Junmo Kim
摘要
Unlearning in large language models (LLMs) has emerged as a promising safeguard against adversarial behaviors. When the forgetting loss is applied uniformly without considering token-level semantic importance, model utility can be unnecessarily degraded. Recent studies have explored token-wise lo...