作者位次 #7/9ACL 2026Findings· Findings of ACL
Self-Explaining Hate Speech Detection with Moral Rationales
Francielle Vargas · Jackson Trager · Diego Alves · Matteo Guida · Surendrabikram Thapa · Berk Atıl · Daryna Dementieva · Andrew J Smart · Ameeta Agrawal
摘要
Existing hate speech detection models are often opaque and rely on surface-level lexical cues, which makes them vulnerable to spurious correlations and limits robustness, interpretability and cultural contextualization. We propose Supervised Moral Rationale Attention (SMRA), the first self-explai...