SUBDATA standardizes ten hate speech datasets into one taxonomy, and a demonstration shows left-aligned LLM personas classify more hate speech than right-aligned personas across all target groups.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs
SUBDATA standardizes ten hate speech datasets into one taxonomy, and a demonstration shows left-aligned LLM personas classify more hate speech than right-aligned personas across all target groups.