大模型如何精准“遗忘”敏感数据又不伤能力？这项自校准对齐方案给出新思路。
arXiv:2602.02824v2 Announce Type: replace Abstract: LLM unlearning aims to remove the influence of undesirable knowledge from pretrained language mode…
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…
揭秘大模型智能体如何通过工具实现“遗忘”，为安全与能力平衡提供新思路。
arXiv:2608.21544v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can…
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…
系统检验机器遗忘算法在极端压力下的鲁棒性，为隐私保护研究划出新基准。
arXiv:2608.22527v1 Announce Type: new Abstract: Recently, machine unlearning, the removal of specific training data influence from a model, has gained…
大模型微调后“知道却说不出口”的难题，用召回锚定蒸馏可精准破解。
arXiv:2608.20794v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation …
大模型也需“无痕模式”，Redakto为LLM对话提供隐私保护新方案。
arXiv:2608.18260v1 Announce Type: new Abstract: Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge i…
用机器遗忘替代昂贵的人类反馈，低成本实现大模型偏好对齐，ICML 2026新思路。
arXiv:2504.06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream m…
SAUL把锐度感知与增强拉格朗日结合，给机器遗忘难题开了一剂新药方。
arXiv:2608.16249v1 Announce Type: new Abstract: Machine unlearning in Large Language Models (LLMs) faces a critical trade-off between erasing target k…
从几何视角剖析持续学习中的表征漂移，揭示灾难性遗忘的内在机制，为构建不退化的智能模型提供新思路。
arXiv:2608.15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lo…
白盒研究揭示大模型遗忘后的恢复规律，用测量替代优化，为LLM安全删除提供新视角。
arXiv:2608.11408v1 Announce Type: new Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge a…
多模态大模型遗忘新思路，模型合并实现持续去学习，破解隐私与安全难题。
arXiv:2608.04548v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) unlearning methods have been proposed to remove private, sens…
大模型遗忘难题新解，轨迹引导网络实现精准、可持续的知识擦除，兼顾隐私与性能。
arXiv:2608.03123v1 Announce Type: new Abstract: Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, un…
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…
针对多模态大模型遗忘任务中数据不平衡引发的公平性挑战，提出全新基准与评估方法
arXiv:2607.21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply wi…
RAG系统如何实现知识“遗忘”？这篇IEEE论文探讨机器遗忘与检索增强生成的交叉，让AI既能记住也能忘掉秘密，挑战隐私与性能的平衡。
arXiv:2410.15267v3 Announce Type: replace-cross Abstract: The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their power…
提出混合子专家架构，让大模型持续学习时有效缓解灾难性遗忘，兼顾精度与效率。
arXiv:2511.06237v2 Announce Type: replace Abstract: Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., model…
文丨小葵 编辑丨果脯 7月9日，网易旗下Joker工作室端出了他们打磨了七年的作品——《遗忘之海》，一款海洋奇遇大世界RPG。PC端率先公测，移动端版本将在7月23日与玩家见面。 这款怪诞木偶风的航海游戏，还没出海就已经被盯上了。在公测前夕，这款游戏全网预约量已突破3600万，在TapTap、B站等…
突破LLM持续微调遗忘瓶颈，ReCoLoRA以频谱感知递归合并实现任务序列高效学习。
arXiv:2607.07719v1 Announce Type: new Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task s…
IT之家 7 月 9 日消息，网易 Joker 工作室继《第五人格》后耗时 7 年打造的海洋冒险 RPG《遗忘之海》PC 版今日正式公测。游戏此前已于 7 月 6 日上午 10 时开启预下载。 官方表示，《遗忘之海》相同账号在不同平台（PC / iOS / 安卓）数据互通，各平台均为同一 UID，且…