@inproceedings{tekgurler-2025-llms,
title = "{LLM}s for Translation: Historical, Low-Resourced Languages and Contemporary {AI} Models",
author = {Tekg{\"u}rler, Merve},
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-1.20/",
doi = "10.18653/v1/2025.latechclfl-1.20",
pages = "227--237",
ISBN = "979-8-89176-241-1",
abstract = "Large Language Models (LLMs) have demonstrated remarkable adaptability in performing various tasks, including machine translation (MT), without explicit training. Models such as OpenAI{'}s GPT-4 and Google{'}s Gemini are frequently evaluated on translation benchmarks and utilized as translation tools due to their high performance. This paper examines Gemini{'}s performance in translating an 18th-century Ottoman Turkish manuscript, Prisoner of the Infidels: The Memoirs of Osman Agha of Timișoara, into English. The manuscript recounts the experiences of Osman Agha, an Ottoman subject who spent 11 years as a prisoner of war in Austria, and includes his accounts of warfare and violence. Our analysis reveals that Gemini{'}s safety mechanisms flagged between 14{\%} and 23{\%} of the manuscript as harmful, resulting in untranslated passages. These safety settings, while effective in mitigating potential harm, hinder the model{'}s ability to provide complete and accurate translations of historical texts. Through real historical examples, this study highlights the inherent challenges and limitations of current LLM safety implementations in the handling of sensitive and context-rich materials. These real-world instances underscore potential failures of LLMs in contemporary translation scenarios, where accurate and comprehensive translations are crucial{---}for example, translating the accounts of modern victims of war for legal proceedings or humanitarian documentation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tekgurler-2025-llms">
<titleInfo>
<title>LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Merve</namePart>
<namePart type="family">Tekgürler</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>Large Language Models (LLMs) have demonstrated remarkable adaptability in performing various tasks, including machine translation (MT), without explicit training. Models such as OpenAI’s GPT-4 and Google’s Gemini are frequently evaluated on translation benchmarks and utilized as translation tools due to their high performance. This paper examines Gemini’s performance in translating an 18th-century Ottoman Turkish manuscript, Prisoner of the Infidels: The Memoirs of Osman Agha of Timișoara, into English. The manuscript recounts the experiences of Osman Agha, an Ottoman subject who spent 11 years as a prisoner of war in Austria, and includes his accounts of warfare and violence. Our analysis reveals that Gemini’s safety mechanisms flagged between 14% and 23% of the manuscript as harmful, resulting in untranslated passages. These safety settings, while effective in mitigating potential harm, hinder the model’s ability to provide complete and accurate translations of historical texts. Through real historical examples, this study highlights the inherent challenges and limitations of current LLM safety implementations in the handling of sensitive and context-rich materials. These real-world instances underscore potential failures of LLMs in contemporary translation scenarios, where accurate and comprehensive translations are crucial—for example, translating the accounts of modern victims of war for legal proceedings or humanitarian documentation.</abstract>
<identifier type="citekey">tekgurler-2025-llms</identifier>
<identifier type="doi">10.18653/v1/2025.latechclfl-1.20</identifier>
<location>
<url>https://aclanthology.org/2025.latechclfl-1.20/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>227</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models
%A Tekgürler, Merve
%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 tekgurler-2025-llms
%X Large Language Models (LLMs) have demonstrated remarkable adaptability in performing various tasks, including machine translation (MT), without explicit training. Models such as OpenAI’s GPT-4 and Google’s Gemini are frequently evaluated on translation benchmarks and utilized as translation tools due to their high performance. This paper examines Gemini’s performance in translating an 18th-century Ottoman Turkish manuscript, Prisoner of the Infidels: The Memoirs of Osman Agha of Timișoara, into English. The manuscript recounts the experiences of Osman Agha, an Ottoman subject who spent 11 years as a prisoner of war in Austria, and includes his accounts of warfare and violence. Our analysis reveals that Gemini’s safety mechanisms flagged between 14% and 23% of the manuscript as harmful, resulting in untranslated passages. These safety settings, while effective in mitigating potential harm, hinder the model’s ability to provide complete and accurate translations of historical texts. Through real historical examples, this study highlights the inherent challenges and limitations of current LLM safety implementations in the handling of sensitive and context-rich materials. These real-world instances underscore potential failures of LLMs in contemporary translation scenarios, where accurate and comprehensive translations are crucial—for example, translating the accounts of modern victims of war for legal proceedings or humanitarian documentation.
%R 10.18653/v1/2025.latechclfl-1.20
%U https://aclanthology.org/2025.latechclfl-1.20/
%U https://doi.org/10.18653/v1/2025.latechclfl-1.20
%P 227-237
Markdown (Informal)
[LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models](https://aclanthology.org/2025.latechclfl-1.20/) (Tekgürler, LaTeCHCLfL 2025)
ACL