研究人员正在开发先进的大语言模型（LLM）遗忘技术，重点关注能够抵御重新学习攻击并保持模型效用的方法。BLADE和Margin Calibration (MC)等新方法旨在提高对遗忘过程的控制力，解决灾难性遗忘和信息删除脆弱性等问题。这些方法正在各种基准和模型规模上进行评估，重点关注对抗鲁棒性，以确保通过战略性提示无法轻易恢复被遗忘的信息。 AI
影响 大语言模型遗忘技术的进步可以通过更可靠地删除敏感或不希望的数据来增强AI安全和隐私。
排序理由 该集群包含多篇详细介绍大语言模型遗忘新方法和评估的学术论文。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.25429v1 Announce Type: cross Abstract: Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed knowledge. Existing robustness predictors rely on global weight-space displacement…
arXiv:2608.22557v1 Announce Type: cross Abstract: Existing LLM unlearning methods struggle with robustness: unbounded forget losses degrade model coherence, fixed-weight balancing cannot adapt as retain difficulty shifts mid-training, and methods that work on one benchmark falter…
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for every method we evaluate, and we trace this fragi…
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whether such information has truly become inaccessible remains challenging. Existing …
arXiv:2602.02824v2 Announce Type: replace Abstract: LLM unlearning aims to remove the influence of undesirable knowledge from pretrained language models, which offers a practical mechanism for addressing safety and privacy concerns. Existing unlearning approaches, such as Gradien…
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…