Machine unlearning aims to remove specific content from trained models while preserving overall performance. However, the phenomenon of benign relearning, in which forgotten information reemerges even from benign fine-tuning data, reveals that existing unlearning methods remain fundamentally fragile. A common explanation attributes this effect to topical relevance, but we find this account insufficient. Through systematic analysis, we demonstrate that syntactic similarity, rather than topicality, is the primary driver: across benchmarks, syntactically similar data consistently trigger recovery even without topical overlap, due to their alignment in representations and gradients with the forgotten content. Motivated by this insight, we introduce syntactic diversification, which paraphrases the original forget queries into heterogeneous structures prior to unlearning. This approach effectively suppresses benign relearning, accelerates forgetting, and substantially alleviates the trade-off between unlearning efficacy and model utility.
FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
School of Cyber Engineering, Xidian University（电子科技大学信息工程学院）；RMIT University（皇家墨尔本理工大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（澳大利亚联邦科学与工业研究组织）；UNSW Sydney（新南威尔士大学悉尼分校）；University of California, Davis（加州大学戴维斯分校）
Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
Graduate School of Artificial Intelligence, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea（人工智能研究生院，乌山国立科学与技术研究所（UNIST），乌山，韩国）；Department of Industrial Engineering, UNIST, Ulsan, South Korea（工业工程系，UNIST，乌山，韩国）；Department of Electrical Engineering, UNIST, Ulsan, South Korea（电气工程系，UNIST，乌山，韩国）
Rethinking Machine Unlearning for Large Language Models
Michigan State University（密歇根州立大学）；IBM Research（IBM研究院）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；ByteDance Research（字节跳动研究院）；Stanford University（斯坦福大学）
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
The Hong Kong Polytechnic University（香港理工大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Santa Cruz（加州大学圣克ruz分校）；Huawei Technologies（华为技术有限公司）；Research Centre for Privacy and Security Technologies in Future Smart Systems, PolyU（未来智能系统中的隐私与安全技术研究中心，PolyU）
Not All Change Is Damage: Update-Matched Unlearning for Large Language Models
Technische Universität Berlin（柏林工业大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）
Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
Department of Statistics and Data Science（统计与数据科学系）；Northwestern University（西北大学）；Department of Computer Science and Engineering（计算机科学与工程系）；University of Notre Dame（圣母大学）；Department of Computer Science（计算机科学系）；Illinois Institute of Technology（伊利诺伊理工学院）
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；Institute for AI, Tsinghua University（清华大学人工智能研究院）；Huzhou University（湖州大学）；Institute of Dataspace, Hefei Comprehensive National Science Center（合肥综合性国家科学中心数据空间研究院）；University of Science and Technology of China（中国科学技术大学）
Towards Irreversible Machine Unlearning for Diffusion Models
Department of Electrical and Computer Engineering, College of Design and Engineering, National University of Singapore（新加坡国立大学电子与计算机工程系，设计与工程学院）；Betterdata, Singapore（新加坡Betterdata公司）；Department of Computer Science, University of Sheffield（谢菲尔德大学计算机科学系）
