Censored LLMs achieve 69.0% strict accuracy in hate speech detection versus 64.1% for uncensored models and resist persona-based ideological influence better, but all exhibit overconfidence, irony failures, and group fairness disparities.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
Censored LLMs achieve 69.0% strict accuracy in hate speech detection versus 64.1% for uncensored models and resist persona-based ideological influence better, but all exhibit overconfidence, irony failures, and group fairness disparities.