一作ICML 2026Oral· Deep Learning / Large Language Models
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
Jianhui Chen · Yuzhang Luo · Liangming Pan
可解释性OpenReview
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。
Jianhui Chen · Yuzhang Luo · Liangming Pan
Yi Hu · Jiaqi Gu · Ruxin Wang · Zijun Yao · Hao Peng · Xiaobao Wu · Jianhui Chen · Muhan Zhang · Liangming Pan
Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnered significant excitement, exploring the internal mechanisms driving these behaviors has become an equally critical re...