作者位次 #3/4ICLR 2026Poster· Social Aspects / Accountability, Transparency and Interpretability
LLMs Process Lists With General Filter Heads
Arnab Sen Sharma · Giordano Rogers · Natalie Shapira · David Bau
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。
Arnab Sen Sharma · Giordano Rogers · Natalie Shapira · David Bau
Nikhil Prakash · Natalie Shapira · Arnab Sen Sharma · Christoph Riedl · Yonatan Belinkov · Tamar Shaham · David Bau · Atticus Geiger
Hail Hochman · Natalie Shapira · Yoav Goldberg
Large language models (LLMs) store and recall factual knowledge, yet the precise mechanism of how entity representations are transformed to enable specific attribute retrieval remains underexplored. In this work, we investigate this mechanism through the lens of an “attribute-computation path”—a...