@inproceedings{morand-etal-2026-tommer,
title = "{T}o{MM}e{R} - Efficient Entity Mention Detection from Large Language Models",
author = "Morand, Victor and
Tomeh, Nadi and
Mothe, Josiane and
Piwowarski, Benjamin",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1268/",
pages = "27489--27509",
ISBN = "979-8-89176-390-6",
abstract = "Identifying which text spans refer to entities - mention detection- is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a lightweight model ({\ensuremath{<}}300K parameters) probing mention detection capabilities from early LLM layers. Across 13 NER benchmarks, ToMMeR achieves 93{\%} recall zero-shot, with an estimated 90{\%} precision under a human-calibrated LLM-judge protocol, showing that ToMMeR rarely produces spurious predictions despite high recall. Cross-model analysis reveals that diverse architectures (14M-15B parameters) converge on similar mention boundaries (DICE {\ensuremath{>}}75{\%}), confirming that mention detection emerges naturally from language modeling. When extended with span classification heads, ToMMeR achieves competitive NER performance (80-87{\%} F1 on standard benchmarks). Our work provides evidence that structured entity representations exist in early transformer layers and can be efficiently recovered with minimal parameters."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morand-etal-2026-tommer">
<titleInfo>
<title>ToMMeR - Efficient Entity Mention Detection from Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Morand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josiane</namePart>
<namePart type="family">Mothe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Piwowarski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Identifying which text spans refer to entities - mention detection- is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a lightweight model (\ensuremath<300K parameters) probing mention detection capabilities from early LLM layers. Across 13 NER benchmarks, ToMMeR achieves 93% recall zero-shot, with an estimated 90% precision under a human-calibrated LLM-judge protocol, showing that ToMMeR rarely produces spurious predictions despite high recall. Cross-model analysis reveals that diverse architectures (14M-15B parameters) converge on similar mention boundaries (DICE \ensuremath>75%), confirming that mention detection emerges naturally from language modeling. When extended with span classification heads, ToMMeR achieves competitive NER performance (80-87% F1 on standard benchmarks). Our work provides evidence that structured entity representations exist in early transformer layers and can be efficiently recovered with minimal parameters.</abstract>
<identifier type="citekey">morand-etal-2026-tommer</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1268/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>27489</start>
<end>27509</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ToMMeR - Efficient Entity Mention Detection from Large Language Models
%A Morand, Victor
%A Tomeh, Nadi
%A Mothe, Josiane
%A Piwowarski, Benjamin
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F morand-etal-2026-tommer
%X Identifying which text spans refer to entities - mention detection- is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a lightweight model (\ensuremath<300K parameters) probing mention detection capabilities from early LLM layers. Across 13 NER benchmarks, ToMMeR achieves 93% recall zero-shot, with an estimated 90% precision under a human-calibrated LLM-judge protocol, showing that ToMMeR rarely produces spurious predictions despite high recall. Cross-model analysis reveals that diverse architectures (14M-15B parameters) converge on similar mention boundaries (DICE \ensuremath>75%), confirming that mention detection emerges naturally from language modeling. When extended with span classification heads, ToMMeR achieves competitive NER performance (80-87% F1 on standard benchmarks). Our work provides evidence that structured entity representations exist in early transformer layers and can be efficiently recovered with minimal parameters.
%U https://aclanthology.org/2026.acl-long.1268/
%P 27489-27509
Markdown (Informal)
[ToMMeR - Efficient Entity Mention Detection from Large Language Models](https://aclanthology.org/2026.acl-long.1268/) (Morand et al., ACL 2026)
ACL
- Victor Morand, Nadi Tomeh, Josiane Mothe, and Benjamin Piwowarski. 2026. ToMMeR - Efficient Entity Mention Detection from Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 27489–27509, San Diego, California, United States. Association for Computational Linguistics.