EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
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 alignment properties they are meant to represent remain uncertain. Synthesizing 373 primary studies published between 2018 and 2026, the survey organizes evidence on benchmark validity, contamination, dynamic evaluation, LLM-as-a-judge protocols, adversarial safety testing, reward and proxy optimization, mechanistic interpretability, and AI governance into an eight-stream evidence taxonomy. Building on this synthesis, we introduce EvalSaf...
| Authors | Buğra Alperen Uluırmak, Rifat Kurban |
|---|---|
| Primary category | cs.AI |
| Published | 29 June 2026 |
| Last updated at source | 31 July 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.