作者位次 #2/4ICLR 2026Poster· Social Aspects / Accountability, Transparency and Interpretability
Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto · Ryoma Kumon · Danushka Bollegala · Hitomi Yanaka
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。
Taisei Yamamoto · Ryoma Kumon · Danushka Bollegala · Hitomi Yanaka
Ryoma Kumon · Hitomi Yanaka
While language models demonstrate sophisticated syntactic capabilities, the extent to which their internal mechanisms align with cross-constructional principles studied in linguistics remains poorly understood. This study investigates whether models employ shared neural mechanisms across differen...
Jin Tanaka · Daiki Matsuoka · Ryoma Kumon · Hitomi Yanaka
We investigate the extent to which the language processing of LLMs resembles human cognitive processes, focusing on a human cognitive bias called the neglect-zero effect . This effect refers to the human tendency to ignore zero-models , which are configurations that render a proposition vacuously...