2 papers
cs.CL2026
When Does Span-Guided Detoxification Help? Human Preferences and Evaluator Diagnostics in a Controlled Comparison
Kyungwon Park
Span-guided rewriting aims to preserve meaning by localizing edits to annotated harmful spans, but the same constraint can leave harmful intent insufficiently mitigated. We present…
cs.CL2026
AEGIS: Awareness-Enhanced Guidance for Iterative Safeguard
Kyungwon Park, Sangmin Lee, Heejae Chon +1
Span-level rationales are often assumed to improve controllability in text detoxification, but it remains unclear when such guidance helps and when it introduces trade-offs. We pre…