Tag
This paper presents a controlled comparison of span-guided and unguided text detoxification via human evaluation, finding a trade-off: span-guided rewriting is preferred when preserving original stance is important, while unguided rewriting is favored for more complete mitigation, especially on milder toxicity. The study also assesses automatic evaluators as diagnostics rather than substitutes for human judgment.
AEGIS is an exploratory framework for studying span-level guided multilingual detoxification across English, Mandarin Chinese, and Korean, analyzing how explicit rationales affect the trade-off between toxicity reduction and meaning preservation.