Exploring Hybrid Pre-training for Automatic Essay Scoring

Miguel Carpi; Igor C. Silveira; Denis D. Mauá; Marcelo Finger

doi:10.5753/stil.2026.26589

Exploring Hybrid Pre-training for Automatic Essay Scoring

Miguel M. Carpi, Igor C. Silveira, Denis D. Mauá, Marcelo Finger

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

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>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

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

Alternatives to Large Language Models have been proposed to develop smaller models that require substantially less training data. In this paper, we propose a monolingual (Portuguese) Hybrid Transformer model trained with only 260M words, whose size is comparable to that of small Encoder-based models. After pre-training, we fine-tune our model and compare it against 11 existing models on the AES-ENEM dataset — an Automatic Essay Scoring benchmark in which models are required to evaluate five distinct textual dimensions. Our experiments demonstrate that our model is always competitive with the (bigger) best available model, despite its smaller scale.

Anthology ID:: 2026.stil-1.6
Volume:: Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
Month:: October
Year:: 2026
Address:: Cuiabá, Mato Grosso, Brazil
Editors:: Bryan Khelven da Silva Barbosa, Aline Paes, Ariani Di Felippo
Venue:: STIL
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 62–77
Language:
URL:: https://aclanthology.org/2026.stil-1.6/
DOI:: 10.5753/stil.2026.26589
Bibkey:
Cite (ACL):: Miguel M. Carpi, Igor C. Silveira, Denis D. Mauá, and Marcelo Finger. 2026. Exploring Hybrid Pre-training for Automatic Essay Scoring. In Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology, pages 62–77, Cuiabá, Mato Grosso, Brazil. Association for Computational Linguistics.
Cite (Informal):: Exploring Hybrid Pre-training for Automatic Essay Scoring (Carpi et al., STIL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.stil-1.6.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{carpi-etal-2026-exploring,
    title = "Exploring Hybrid Pre-training for Automatic Essay Scoring",
    author = "Carpi, Miguel M.  and
      Silveira, Igor C.  and
      Mau{\'a}, Denis D.  and
      Finger, Marcelo",
    editor = "Barbosa, Bryan Khelven da Silva  and
      Paes, Aline  and
      Felippo, Ariani Di",
    booktitle = "Proceedings of the 17th {B}razilian Symposium in Information and Human Language Technology",
    month = oct,
    year = "2026",
    address = "Cuiab{\'a}, Mato Grosso, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.stil-1.6/",
    doi = "10.5753/stil.2026.26589",
    pages = "62--77",
    abstract = "Alternatives to Large Language Models have been proposed to develop smaller models that require substantially less training data. In this paper, we propose a monolingual (Portuguese) Hybrid Transformer model trained with only 260M words, whose size is comparable to that of small Encoder-based models. After pre-training, we fine-tune our model and compare it against 11 existing models on the AES-ENEM dataset {---} an Automatic Essay Scoring benchmark in which models are required to evaluate five distinct textual dimensions. Our experiments demonstrate that our model is always competitive with the (bigger) best available model, despite its smaller scale."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carpi-etal-2026-exploring">
    <titleInfo>
        <title>Exploring Hybrid Pre-training for Automatic Essay Scoring</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Miguel</namePart>
        <namePart type="given">M</namePart>
        <namePart type="family">Carpi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Igor</namePart>
        <namePart type="given">C</namePart>
        <namePart type="family">Silveira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Denis</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Mauá</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marcelo</namePart>
        <namePart type="family">Finger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bryan</namePart>
            <namePart type="given">Khelven</namePart>
            <namePart type="given">da</namePart>
            <namePart type="given">Silva</namePart>
            <namePart type="family">Barbosa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Paes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ariani</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Felippo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Alternatives to Large Language Models have been proposed to develop smaller models that require substantially less training data. In this paper, we propose a monolingual (Portuguese) Hybrid Transformer model trained with only 260M words, whose size is comparable to that of small Encoder-based models. After pre-training, we fine-tune our model and compare it against 11 existing models on the AES-ENEM dataset — an Automatic Essay Scoring benchmark in which models are required to evaluate five distinct textual dimensions. Our experiments demonstrate that our model is always competitive with the (bigger) best available model, despite its smaller scale.</abstract>
    <identifier type="citekey">carpi-etal-2026-exploring</identifier>
    <identifier type="doi">10.5753/stil.2026.26589</identifier>
    <location>
        <url>https://aclanthology.org/2026.stil-1.6/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>62</start>
            <end>77</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Exploring Hybrid Pre-training for Automatic Essay Scoring
%A Carpi, Miguel M.
%A Silveira, Igor C.
%A Mauá, Denis D.
%A Finger, Marcelo
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F carpi-etal-2026-exploring
%X Alternatives to Large Language Models have been proposed to develop smaller models that require substantially less training data. In this paper, we propose a monolingual (Portuguese) Hybrid Transformer model trained with only 260M words, whose size is comparable to that of small Encoder-based models. After pre-training, we fine-tune our model and compare it against 11 existing models on the AES-ENEM dataset — an Automatic Essay Scoring benchmark in which models are required to evaluate five distinct textual dimensions. Our experiments demonstrate that our model is always competitive with the (bigger) best available model, despite its smaller scale.
%R 10.5753/stil.2026.26589
%U https://aclanthology.org/2026.stil-1.6/
%U https://doi.org/10.5753/stil.2026.26589
%P 62-77

Download as File

Markdown (Informal)

[Exploring Hybrid Pre-training for Automatic Essay Scoring](https://aclanthology.org/2026.stil-1.6/) (Carpi et al., STIL 2026)

Exploring Hybrid Pre-training for Automatic Essay Scoring (Carpi et al., STIL 2026)

ACL

Miguel M. Carpi, Igor C. Silveira, Denis D. Mauá, and Marcelo Finger. 2026. Exploring Hybrid Pre-training for Automatic Essay Scoring. In Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology, pages 62–77, Cuiabá, Mato Grosso, Brazil. Association for Computational Linguistics.