JADR Protocol Measures Internal Danger Recognition in LLMs Without External Judges

Jul 15, 2026

Researchers introduce JADR (Jacobian Assessment of Danger Recognition), a protocol that evaluates a language model's internal representation of danger by analyzing Jacobian space activations before any response is generated. The method operates entirely locally, does not require external judge models, and enables comparison of models and quantization levels using a SafetyAUC metric with statistical significance. Applied to six models, including Qwen3 variants and Gemma 2 9B, JADR distinguishes between strong and weak internal safety mechanisms and reveals quantization effects.

Why it matters: This approach provides a novel, judge-free method for probing LLM safety by examining internal model activations, potentially uncovering hidden vulnerabilities in safety mechanisms.

Full story at: arXiv Cryptography and Security ↗