LLM safety judges resist adjusting evaluations when given contradictory context or new safety definitions, despite some ability to learn from new information.
From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators
LLM safety judges resist adjusting evaluations when given contradictory context or new safety definitions, despite some ability to learn from new information.
- LLM Harms: A Taxonomy and Discussion