<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosu-2025-litera">
    <titleInfo>
        <title>LITERA: An LLM Based Approach to Latin-to-English Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Paul</namePart>
        <namePart type="family">Rosu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</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">979-8-89176-195-7</identifier>
    </relatedItem>
    <abstract>This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University’s Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.</abstract>
    <identifier type="citekey">rosu-2025-litera</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.434</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.434/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>7781</start>
            <end>7794</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LITERA: An LLM Based Approach to Latin-to-English Translation
%A Rosu, Paul
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F rosu-2025-litera
%X This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University’s Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.
%R 10.18653/v1/2025.findings-naacl.434
%U https://aclanthology.org/2025.findings-naacl.434/
%U https://doi.org/10.18653/v1/2025.findings-naacl.434
%P 7781-7794

Markdown (Informal)

[LITERA: An LLM Based Approach to Latin-to-English Translation](https://aclanthology.org/2025.findings-naacl.434/) (Rosu, Findings 2025)

• LITERA: An LLM Based Approach to Latin-to-English Translation (Rosu, Findings 2025)

ACL

• Paul Rosu. 2025. LITERA: An LLM Based Approach to Latin-to-English Translation. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7781–7794, Albuquerque, New Mexico. Association for Computational Linguistics.