LLM safety judges are inconsistent and disagree with each other, especially on regulated-domain advice like finance, while performing better on overt harms like violence; inconsistency also varies by language and style.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
LLM safety judges are inconsistent and disagree with each other, especially on regulated-domain advice like finance, while performing better on overt harms like violence; inconsistency also varies by language and style.