@inproceedings{bagdasarov-etal-2026-using,
title = "Using {LLM}s for Automatic Discipline Annotation in a Diachronic Corpus of {E}nglish Scientific Papers",
author = "Bagdasarov, Sergei and
Alves, Diego and
Fischer, Stefan and
Teich, Elke",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.187/",
doi = "10.63317/3j9wvu86v48t",
pages = "2376--2386",
abstract = "This study investigates the potential of generative large language models (LLMs) to automatically identify the disciplines of scientific papers in the Royal Society Corpus (RSC) {--} an extensive collection of English scientific publications spanning more than three centuries. We evaluated eight open-source, state-of-the-art LLMs from four model families on a manually annotated subset and further validated the three best-performing models on a corpus of modern scientific texts. These models were subsequently used for large-scale annotation of the RSC. The models exhibited robust and consistent performance, with at least two LLMs agreeing on the same label for 98.3{\%} of the documents. We then conducted an error analysis of papers assigned divergent labels and a diachronic case study of disciplinary trends within the corpus. The error analysis revealed that most discrepancies occurred in twentieth-century texts, reflecting the growing interdisciplinarity of research. The diachronic analysis showed a gradual decline in disciplinary diversity over time as well as fluctuations corresponding to major paradigm shifts such as the Chemical Revolution and key twentieth-century developments in Physics. The discipline labels generated by the three models will be made publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bagdasarov-etal-2026-using">
<titleInfo>
<title>Using LLMs for Automatic Discipline Annotation in a Diachronic Corpus of English Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergei</namePart>
<namePart type="family">Bagdasarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Fischer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elke</namePart>
<namePart type="family">Teich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study investigates the potential of generative large language models (LLMs) to automatically identify the disciplines of scientific papers in the Royal Society Corpus (RSC) – an extensive collection of English scientific publications spanning more than three centuries. We evaluated eight open-source, state-of-the-art LLMs from four model families on a manually annotated subset and further validated the three best-performing models on a corpus of modern scientific texts. These models were subsequently used for large-scale annotation of the RSC. The models exhibited robust and consistent performance, with at least two LLMs agreeing on the same label for 98.3% of the documents. We then conducted an error analysis of papers assigned divergent labels and a diachronic case study of disciplinary trends within the corpus. The error analysis revealed that most discrepancies occurred in twentieth-century texts, reflecting the growing interdisciplinarity of research. The diachronic analysis showed a gradual decline in disciplinary diversity over time as well as fluctuations corresponding to major paradigm shifts such as the Chemical Revolution and key twentieth-century developments in Physics. The discipline labels generated by the three models will be made publicly available.</abstract>
<identifier type="citekey">bagdasarov-etal-2026-using</identifier>
<identifier type="doi">10.63317/3j9wvu86v48t</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.187/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2376</start>
<end>2386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using LLMs for Automatic Discipline Annotation in a Diachronic Corpus of English Scientific Papers
%A Bagdasarov, Sergei
%A Alves, Diego
%A Fischer, Stefan
%A Teich, Elke
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F bagdasarov-etal-2026-using
%X This study investigates the potential of generative large language models (LLMs) to automatically identify the disciplines of scientific papers in the Royal Society Corpus (RSC) – an extensive collection of English scientific publications spanning more than three centuries. We evaluated eight open-source, state-of-the-art LLMs from four model families on a manually annotated subset and further validated the three best-performing models on a corpus of modern scientific texts. These models were subsequently used for large-scale annotation of the RSC. The models exhibited robust and consistent performance, with at least two LLMs agreeing on the same label for 98.3% of the documents. We then conducted an error analysis of papers assigned divergent labels and a diachronic case study of disciplinary trends within the corpus. The error analysis revealed that most discrepancies occurred in twentieth-century texts, reflecting the growing interdisciplinarity of research. The diachronic analysis showed a gradual decline in disciplinary diversity over time as well as fluctuations corresponding to major paradigm shifts such as the Chemical Revolution and key twentieth-century developments in Physics. The discipline labels generated by the three models will be made publicly available.
%R 10.63317/3j9wvu86v48t
%U https://aclanthology.org/2026.lrec-1.187/
%U https://doi.org/10.63317/3j9wvu86v48t
%P 2376-2386
Markdown (Informal)
[Using LLMs for Automatic Discipline Annotation in a Diachronic Corpus of English Scientific Papers](https://aclanthology.org/2026.lrec-1.187/) (Bagdasarov et al., LREC 2026)
ACL