Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models 文章

ArXiv CS.AI2026-05-27NEWSen作者: Haoxiang Wang, Da Yu, Huishuai Zhang
大语言模型
查看原文 →
关系图谱

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models · 相关技术

相关技术

Large language modelAPISkillLLMORMODEPLAlanguage modelsafetyevalSAFEQueryPromptParts-of-Speech (POS) tagsLMMGranular Alignment ParadigmForFFICodingCamouflaged object detectionARGANN