1
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
LLM评估与AI安全间存在测量鸿沟,基准分数看似提升但潜在属性难验证,这篇混合调查构建了系统性概念框架
arXiv:2606.30219v1 Announce Type: cross Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signa…