Automated judges for LLM jailbreak ASR show opposite calibration failures and low robustness, with LLM judges flipped by benign framing and classifiers vulnerable to white-box attacks.
Gemma Team, G
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.
citing papers explorer
-
How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring
Automated judges for LLM jailbreak ASR show opposite calibration failures and low robustness, with LLM judges flipped by benign framing and classifiers vulnerable to white-box attacks.
-
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.