作者位次 #4/8ICML 2026Spotlight· General Machine Learning / Evaluation
Do LLMs Signal When They’re Right? Evidence from Neuron Agreement
Kang Chen · Yaoning Wang · Kai Xiong · Zhuoka Feng · Yu Minshen · Wenhe Sun · Haotian Chen · Yixin Cao
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。
Kang Chen · Yaoning Wang · Kai Xiong · Zhuoka Feng · Yu Minshen · Wenhe Sun · Haotian Chen · Yixin Cao
Chenkang · Fan Yu · Junjie Nian · Sihan Zhao · Zhuoka Feng · Zijun Yao · Wang Heng · Yu Minshen · Yixin Cao
Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a self-consistent but incorrect prefix. Through fine-grained trajector...