Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
arXiv preprint arXiv:2110.14839 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
An audit finds language model filters and guardrails disproportionately suppress mentions of marginalized groups via lexical cues while failing to catch explicit harms.
citing papers explorer
-
Understanding Annotator Safety Policy with Interpretability
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
-
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails
An audit finds language model filters and guardrails disproportionately suppress mentions of marginalized groups via lexical cues while failing to catch explicit harms.