Finetuning LLMs for EvaCun 2025 token prediction shared task

Josef Jon; Ondřej Bojar

doi:10.18653/v1/2025.alp-1.29

Finetuning LLMs for EvaCun 2025 token prediction shared task

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simply used the training data without any task-specific adjustments, preprocessing, or filtering. We compare 3 different approaches (based on 3 different prompts) of obtaining the predictions, and we evaluate them on a held-out part of the data.

Anthology ID:: 2025.alp-1.29
Volume:: Proceedings of the Second Workshop on Ancient Language Processing
Month:: May
Year:: 2025
Address:: The Albuquerque Convention Center, Laguna
Editors:: Adam Anderson, Shai Gordin, Bin Li, Yudong Liu, Marco C. Passarotti, Rachele Sprugnoli
Venues:: ALP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 221–225
Language:
URL:: https://aclanthology.org/2025.alp-1.29/
DOI:: 10.18653/v1/2025.alp-1.29
Bibkey:
Cite (ACL):: Josef Jon and Ondřej Bojar. 2025. Finetuning LLMs for EvaCun 2025 token prediction shared task. In Proceedings of the Second Workshop on Ancient Language Processing, pages 221–225, The Albuquerque Convention Center, Laguna. Association for Computational Linguistics.
Cite (Informal):: Finetuning LLMs for EvaCun 2025 token prediction shared task (Jon & Bojar, ALP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.alp-1.29.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{jon-bojar-2025-finetuning,
    title = "Finetuning {LLM}s for {E}va{C}un 2025 token prediction shared task",
    author = "Jon, Josef  and
      Bojar, Ond{\v{r}}ej",
    editor = "Anderson, Adam  and
      Gordin, Shai  and
      Li, Bin  and
      Liu, Yudong  and
      Passarotti, Marco C.  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
    month = may,
    year = "2025",
    address = "The Albuquerque Convention Center, Laguna",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.alp-1.29/",
    doi = "10.18653/v1/2025.alp-1.29",
    pages = "221--225",
    ISBN = "979-8-89176-235-0",
    abstract = "In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simply used the training data without any task-specific adjustments, preprocessing, or filtering. We compare 3 different approaches (based on 3 different prompts) of obtaining the predictions, and we evaluate them on a held-out part of the data."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jon-bojar-2025-finetuning">
    <titleInfo>
        <title>Finetuning LLMs for EvaCun 2025 token prediction shared task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Jon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Bojar</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 Second Workshop on Ancient Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Adam</namePart>
            <namePart type="family">Anderson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shai</namePart>
            <namePart type="family">Gordin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bin</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yudong</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="given">C</namePart>
            <namePart type="family">Passarotti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rachele</namePart>
            <namePart type="family">Sprugnoli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-235-0</identifier>
    </relatedItem>
    <abstract>In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simply used the training data without any task-specific adjustments, preprocessing, or filtering. We compare 3 different approaches (based on 3 different prompts) of obtaining the predictions, and we evaluate them on a held-out part of the data.</abstract>
    <identifier type="citekey">jon-bojar-2025-finetuning</identifier>
    <identifier type="doi">10.18653/v1/2025.alp-1.29</identifier>
    <location>
        <url>https://aclanthology.org/2025.alp-1.29/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>221</start>
            <end>225</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Finetuning LLMs for EvaCun 2025 token prediction shared task
%A Jon, Josef
%A Bojar, Ondřej
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F jon-bojar-2025-finetuning
%X In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simply used the training data without any task-specific adjustments, preprocessing, or filtering. We compare 3 different approaches (based on 3 different prompts) of obtaining the predictions, and we evaluate them on a held-out part of the data.
%R 10.18653/v1/2025.alp-1.29
%U https://aclanthology.org/2025.alp-1.29/
%U https://doi.org/10.18653/v1/2025.alp-1.29
%P 221-225

Download as File

Markdown (Informal)

[Finetuning LLMs for EvaCun 2025 token prediction shared task](https://aclanthology.org/2025.alp-1.29/) (Jon & Bojar, ALP 2025)

Finetuning LLMs for EvaCun 2025 token prediction shared task (Jon & Bojar, ALP 2025)

ACL

Josef Jon and Ondřej Bojar. 2025. Finetuning LLMs for EvaCun 2025 token prediction shared task. In Proceedings of the Second Workshop on Ancient Language Processing, pages 221–225, The Albuquerque Convention Center, Laguna. Association for Computational Linguistics.