作者位次 #2/5NeurIPS 2026Poster
Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
Jing Ren · Bowen Li · Ziqi Xu · Xuechao Yang · Feng Xia
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Jing Ren · Bowen Li · Ziqi Xu · Xuechao Yang · Feng Xia
Shuo Yu · Yingbo Wang · Ruolin Li · Guchun Liu · Yanming Shen · Shaoxiong Ji · Bowen Li · Fengling Han · Xiuzhen Zhang · Feng Xia
Graphs are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottlenecks due to the inherent irregularity of graphs. An innovative solution is converting graphs into textual representat...