作者位次 #5/6ACL 2026Findings· Findings of ACL
Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models
Lanxue Zhang · Yuqiang Xie · Fang Fang · Yubing Ren · Xuebin Wang · Yanan Cao
摘要
Large Language Models exhibit advanced reasoning capabilities that enable them to address complex tasks, but these capabilities also increase the risk of generating harmful content, particularly in multi-turn dialogues. Existing inference-phase safety alignment methods face three major challenges...