一作ACL 2026Poster· Natural Language Processing
Factual Retrieval in LLM s Is a Redundant, Distributed and Non-Contiguous Process
Hail Hochman · Natalie Shapira · Yoav Goldberg
摘要
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...