作者位次 #2/4ACL 2026Findings· Findings of ACL
C ausal D etox: Causal Head Selection and Intervention for Language Model Detoxification
Yian Wang · Yuen Chen · Agam Goyal · Hari Sundaram
摘要
Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CausalDetox, a framework that identifies and intervenes on the specific atten...