作者位次 #2/9AAAI 2026Poster· Artificial Intelligence
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
Shiyao Cui · Xijia Feng · Yingkang Wang · Junxiao Yang · Zhexin Zhang · Biplab Sikdar · Hongning Wang · Han Qiu · Minlie Huang
可解释性OpenReview