@inproceedings{sakata-etal-2025-entity,
    title = "On Entity Identification in Language Models",
    author = "Sakata, Masaki  and
      Heinzerling, Benjamin  and
      Yokoi, Sho  and
      Ito, Takumi  and
      Inui, Kentaro",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.858/",
    pages = "16717--16741",
    ISBN = "979-8-89176-256-5",
    abstract = "We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions.We first formulate two problems of entity mentions {---} ambiguity and variability {---} and propose a framework analogous to clustering quality metrics. Specifically, we quantify through cluster analysis of LM internal representations the extent to which mentions of the same entity cluster together and mentions of different entities remain separated.Our experiments examine five Transformer-based autoregressive models, showing that they effectively identify and distinguish entities with metrics analogous to precision and recall ranging from 0.66 to 0.9.Further analysis reveals that entity-related information is compactly represented in a low-dimensional linear subspace at early LM layers.Additionally, we clarify how the characteristics of entity representations influence word prediction performance.These findings are interpreted through the lens of isomorphism between LM representations and entity-centric knowledge structures in the real world, providing insights into how LMs internally organize and use entity information."
}