@inproceedings{tudor-etal-2025-prompting,
title = "Prompting the Past: Exploring Zero-Shot Learning for Named Entity Recognition in Historical Texts Using Prompt-Answering {LLM}s",
author = {Tudor, Crina and
Megyesi, Beata and
{\"O}stling, Robert},
editor = "Kazantseva, Anna and
Szpakowicz, Stan and
Degaetano-Ortlieb, Stefania and
Bizzoni, Yuri and
Pagel, Janis",
booktitle = "Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.latechclfl-1.19/",
doi = "10.18653/v1/2025.latechclfl-1.19",
pages = "216--226",
ISBN = "979-8-89176-241-1",
abstract = "This paper investigates the application of prompt-answering Large Language Models (LLMs) for the task of Named Entity Recognition (NER) in historical texts. Historical NER presents unique challenges due to language change through time, spelling variation, limited availability of digitized data (and, in particular, labeled data), and errors introduced by Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) processes. Leveraging the zero-shot capabilities of prompt-answering LLMs, we address these challenges by prompting the model to extract entities such as persons, locations, organizations, and dates from historical documents. We then conduct an extensive error analysis of the model output in order to identify and address potential weaknesses in the entity recognition process. The results show that, while such models display ability for extracting named entities, their overall performance is lackluster. Our analysis reveals that model performance is significantly affected by hallucinations in the model output, as well as by challenges imposed by the evaluation of NER output."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tudor-etal-2025-prompting">
<titleInfo>
<title>Prompting the Past: Exploring Zero-Shot Learning for Named Entity Recognition in Historical Texts Using Prompt-Answering LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Östling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janis</namePart>
<namePart type="family">Pagel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-241-1</identifier>
</relatedItem>
<abstract>This paper investigates the application of prompt-answering Large Language Models (LLMs) for the task of Named Entity Recognition (NER) in historical texts. Historical NER presents unique challenges due to language change through time, spelling variation, limited availability of digitized data (and, in particular, labeled data), and errors introduced by Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) processes. Leveraging the zero-shot capabilities of prompt-answering LLMs, we address these challenges by prompting the model to extract entities such as persons, locations, organizations, and dates from historical documents. We then conduct an extensive error analysis of the model output in order to identify and address potential weaknesses in the entity recognition process. The results show that, while such models display ability for extracting named entities, their overall performance is lackluster. Our analysis reveals that model performance is significantly affected by hallucinations in the model output, as well as by challenges imposed by the evaluation of NER output.</abstract>
<identifier type="citekey">tudor-etal-2025-prompting</identifier>
<identifier type="doi">10.18653/v1/2025.latechclfl-1.19</identifier>
<location>
<url>https://aclanthology.org/2025.latechclfl-1.19/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>216</start>
<end>226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompting the Past: Exploring Zero-Shot Learning for Named Entity Recognition in Historical Texts Using Prompt-Answering LLMs
%A Tudor, Crina
%A Megyesi, Beata
%A Östling, Robert
%Y Kazantseva, Anna
%Y Szpakowicz, Stan
%Y Degaetano-Ortlieb, Stefania
%Y Bizzoni, Yuri
%Y Pagel, Janis
%S Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-241-1
%F tudor-etal-2025-prompting
%X This paper investigates the application of prompt-answering Large Language Models (LLMs) for the task of Named Entity Recognition (NER) in historical texts. Historical NER presents unique challenges due to language change through time, spelling variation, limited availability of digitized data (and, in particular, labeled data), and errors introduced by Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) processes. Leveraging the zero-shot capabilities of prompt-answering LLMs, we address these challenges by prompting the model to extract entities such as persons, locations, organizations, and dates from historical documents. We then conduct an extensive error analysis of the model output in order to identify and address potential weaknesses in the entity recognition process. The results show that, while such models display ability for extracting named entities, their overall performance is lackluster. Our analysis reveals that model performance is significantly affected by hallucinations in the model output, as well as by challenges imposed by the evaluation of NER output.
%R 10.18653/v1/2025.latechclfl-1.19
%U https://aclanthology.org/2025.latechclfl-1.19/
%U https://doi.org/10.18653/v1/2025.latechclfl-1.19
%P 216-226
Markdown (Informal)
[Prompting the Past: Exploring Zero-Shot Learning for Named Entity Recognition in Historical Texts Using Prompt-Answering LLMs](https://aclanthology.org/2025.latechclfl-1.19/) (Tudor et al., LaTeCHCLfL 2025)
ACL