十四种后处理都扛不住20条样本复学攻击？这项研究用边界校准让LLM遗忘跨过悬崖、真正稳固。
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tunin…
注意力汇成为后门入口，能劫持LLM遗忘机制，COLM 2026研究揭示新型安全威胁。
arXiv:2510.17021v2 Announce Type: replace Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or…
ACL 2026录用，开创性提出前缀感知的局部熵最大化方法，高效实现大模型精准遗忘而不牺牲整体性能。
arXiv:2601.03190v4 Announce Type: replace Abstract: Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while main…
新测试平台LACUNA精准评估大模型遗忘方法，定位精度是关键突破点。
arXiv:2607.02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating…
仅通过API接口实现LLM黑盒遗忘，用行为分歧控制精准擦除特定知识，模型编辑与隐私保护新方向。
arXiv:2606.27683v1 Announce Type: cross Abstract: Edge devices increasingly invoke large language models (LLMs) through API services for context aware…
从分布偏好角度切入，提出细粒度优化方法解决大模型遗忘问题，视角新颖。
arXiv:2510.04773v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpor…
大模型遗忘难题新解法：基于表征选择性实现鲁棒的知识去除，平衡保留与遗忘的边界。
arXiv:2606.17168v1 Announce Type: new Abstract: Making large language models (LLMs) deeply forget specific knowledge and values without sacrificing ge…
对比标准化与模块化采样的最佳实践，为更可靠的LLM遗忘提供关键指导。
arXiv:2509.05316v2 Announce Type: replace-cross Abstract: A conventional LLM Unlearning setting consists of two subsets -"forget" and "retain", with t…
通过学习token级重要性优化大模型遗忘机制，比传统方法更精准高效。
arXiv:2606.06320v1 Announce Type: cross Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its gener…
提出“去属性-遗忘”新方法，让大模型精准擦除特定知识，隐私与安全再升级。
arXiv:2605.30919v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns on the use of inappropriat…
大语言模型的“遗忘”并不彻底，概率解码下仍会泄露被遗忘数据，Leak@k指标揭示这一漏洞。
arXiv:2511.04934v3 Announce Type: replace Abstract: Unlearning in large language models (LLMs) is critical for regulatory compliance and for building …
反事实知识训练虽能帮助LLM遗忘特定信息，但论文揭示其背后的隐藏代价，值得关注。
arXiv:2605.27083v1 Announce Type: new Abstract: Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearn…
通过激活修补技术探究LLM遗忘的深浅程度，为模型安全对齐提供新测量维度
arXiv:2605.24614v1 Announce Type: cross Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protec…