一作ACL 2026Findings· Findings of ACL
T oxi T race: Gradient-Aligned Training for Explainable C hinese Toxicity Detection
Boyang Li · Hongzhe Shou · Yuanyuan Liang · JingBin Zhang · Fang Zhou
摘要
Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose ToxiTrace, an explainability-oriented method for BERT-style encoders with three components: (1) CuSA, which refines encod...