作者位次 #2/3ACL 2026Findings· Findings of ACL
♪ Something Just Like TR u ST ♪ *: Toxicity Recognition of Span and Target
Berk Atıl · Namrata Sureddy · Rebecca J. Passonneau
摘要
Toxic language includes content that is offensive, abusive, or that promotes harm. Progress in preventing toxic output from large language models (LLMs) is hampered by inconsistent definitions of toxicity. We introduce TRuST, a large-scale dataset that unifies and expands prior resources through...