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.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages =
1 Pith paper cite this work, alongside 18 external citations. Polarity classification is still indexing.
1
Pith paper citing it
18
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.