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…
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…
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…
AI模型遗忘的安全隐患触目惊心，SAGE提出后处理方案在保留核心能力的同时彻底清除敏感数据
arXiv:2606.18309v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preservi…
大模型上下文窗口并非越大越好，注意力在10万token后断崖式下降，编码代理人尤其危险。
Article URL: https://garrit.xyz/posts/2026-05-06-dont-trust-large-context-windows Comments URL: https://news.ycombinator.com/item?id=48524620 Points: …
无需保留集！新方法SHRED用自蒸馏+logit降级实现LLM高效遗忘，拒绝灾难性性能下降。
arXiv:2605.07482v2 Announce Type: replace-cross Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized con…
最新研究揭示大模型“遗忘”机制：事实显著性与微调如何双重影响模型知识删除的效果。
arXiv:2602.19612v5 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated informat…
大模型遗忘新方法：几何视角减少数据泄露，训练后只需少量数据即可擦除特定知识。
arXiv:2605.01735v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world systems, they must support…
研究发现大模型遗忘目标需因语言功能而异，为精准删除知识提供新思路。
arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous know…
用对比学习提升机器遗忘效果，解决现有方法遗忘不彻底的问题，为模型数据移除提供新思路。
arXiv:2509.16391v3 Announce Type: replace Abstract: Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained mode…
提出影响力驱动参数重加权方法，高效解决大模型遗忘小样本或不平衡数据的难题。
arXiv:2512.04457v2 Announce Type: replace Abstract: Removing specific data influence from large language models (LLMs) remains challenging, as retrain…
无需修改参数，用提示即可让大模型忘记敏感信息，高效又安全。
arXiv:2604.21251v5 Announce Type: replace-cross Abstract: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensiti…