Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions 文章

ArXiv CS.AI2026-05-26NEWSen作者: Wenjuan Li, Yitao Liu, Runze Chen, Rajkumar Buyya
大语言模型
查看原文 →
关系图谱

Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions · 相关技术

相关技术

ODELLMlanguage modelevaldivide-and-conquer partitioningUnifiedTAMStraight-Through EstimatorSPAReferring expression comprehension (REC)Parts-of-Speech (POS) tagsMITMECLMMlarge language modelsHISFutureForEffort Metric AttentionDAPTARGANNAgent