@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://aclanthology.org/2025.findings-acl.858/",
doi = "10.18653/v1/2025.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakata-etal-2025-entity">
<titleInfo>
<title>On Entity Identification in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Sakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Heinzerling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Yokoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Ito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sakata-etal-2025-entity</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.858</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.858/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>16717</start>
<end>16741</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Entity Identification in Language Models
%A Sakata, Masaki
%A Heinzerling, Benjamin
%A Yokoi, Sho
%A Ito, Takumi
%A Inui, Kentaro
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F sakata-etal-2025-entity
%X 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.
%R 10.18653/v1/2025.findings-acl.858
%U https://aclanthology.org/2025.findings-acl.858/
%U https://doi.org/10.18653/v1/2025.findings-acl.858
%P 16717-16741
Markdown (Informal)
[On Entity Identification in Language Models](https://aclanthology.org/2025.findings-acl.858/) (Sakata et al., Findings 2025)
ACL
- Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, and Kentaro Inui. 2025. On Entity Identification in Language Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16717–16741, Vienna, Austria. Association for Computational Linguistics.