الملخص
Machine unlearning aims to remove target influence while preserving other capabilities. This survey compares methods, benchmarks, and evidence across large language models and systems using retrieval, memory, tools, and interacting agents. A five-layer framework connects removal requests, system boundaries, target locations, interventions, and supported claims. A seven-stage lifecycle and six evidence dimensions guide comparison. The review shows that target construction, retained data, and recovery tests affect reported outcomes. Evidence from model evaluations remains insufficient to establish removal across external state and subsequent updates, motivating evaluation that tracks dependencies and tests whether target influence returns.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xu, X., Du, M., Bai, L., Liu, J., Xiao, Y., Fang, K., Yang, L., Zheng, H., Hu, P., Ye, Q., & Hu, H. (2026). Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions. https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions
MLA 9
Xu, Xiaoyu, et al. "Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions." https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions.
شيكاغو (المؤلف–التاريخ)
Xu, Xiaoyu, Minxin Du, Li Bai, Junxu Liu, Yaxin Xiao, Kun Fang, Liu Yang, Huadi Zheng, Peizhao Hu, Qingqing Ye, and Haibo Hu. 2026. "Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions." https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions.
هارفارد
Xu, X., Du, M., Bai, L., Liu, J., Xiao, Y., Fang, K., Yang, L., Zheng, H., Hu, P., Ye, Q. and Hu, H. (2026) 'Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions', Available at: https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions.
فانكوفر
Xu X, Du M, Bai L, Liu J, Xiao Y, Fang K, et al. Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions. https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions
IEEE
X. Xu, M. Du, L. Bai, J. Liu, Y. Xiao, K. Fang, L. Yang, H. Zheng, P. Hu, Q. Ye, and H. Hu, "Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions," https://omanscience.com/ar/articles/machine-unlearning-for-large-language-models-foundations-advances-and-agentic-extensions.