Marking offensive spans changes — but does not consistently improve — the toxicity–meaning trade-off in multilingual detoxification; the effect depends on the generator backbone and the language.
Hate Speech Classifiers are Culturally Insensitive
1 Pith paper cite this work, alongside 17 external citations. Polarity classification is still indexing.
1
Pith paper citing it
17
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AEGIS: Awareness-Enhanced Guidance for Iterative Safeguard
Marking offensive spans changes — but does not consistently improve — the toxicity–meaning trade-off in multilingual detoxification; the effect depends on the generator backbone and the language.