LLMs show split alignment with human hate speech annotations (strong on explicit attributes, inverted on evaluative ones), and attribute-based ridge regression reconstructs continuous scores with R² up to 0.71.
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
-
Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations
LLMs show split alignment with human hate speech annotations (strong on explicit attributes, inverted on evaluative ones), and attribute-based ridge regression reconstructs continuous scores with R² up to 0.71.