arXiv cs.LG
· Papers
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv:2606.30219v5 Announce Type: replace-cross Abstract: This paper presents a systematic survey and conceptual synthesis of the shared measurement problem underlying large language model (LLM) evaluation and AI safety: benchmark scores, reward signals, and safety metrics can improve while the capabilities and alignme