Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs 文章

ArXiv CS.CL2026-05-27NEWSen作者: Dinesh Srivasthav P, Ashok Urlana, Rahul Mishra, Bala Mallikarjunarao Garlapati, Ponnurangam Kumaraguru
查看原文 →
关系图谱

Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs · 相关技术

相关技术

ORMTTEPLALLM通用表达式语言evalVerseSEMParts-of-Speech (POS) tagsPPROWLMembership Inference AttacksLMMICTHISForEffort Metric AttentionANNMac