ENEM Essay Feedback Using LLM-Augmented Prompts

Flavio Carvalho; Vanessa Soares; Eduardo Bezerra; Gustavo Guedes

doi:10.5753/stil.2026.26575

ENEM Essay Feedback Using LLM-Augmented Prompts

Flavio Carvalho, Vanessa Soares, Eduardo Bezerra, Gustavo Guedes

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

This paper evaluates automated feedback generation for ENEM Competency 5 by augmenting zero-shot prompts with an Evaluator Term Set (CTA), a term set proposed in this work and extracted from human evaluator comments on Competency 5. We compare CTA-augmented feedback against a zero-shot baseline on 46 essays with human reference feedback using BERTScore F1 and the Wilcoxon signed-rank test. CTA augmentation increases mean BERTScore F1 for both models, with statistically significant improvement in semantic similarity to human feedback for both evaluated models at α = 0.05.

Anthology ID:: 2026.stil-1.7
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:: 78–85
Language:
URL:: https://aclanthology.org/2026.stil-1.7/
DOI:: 10.5753/stil.2026.26575
Bibkey:
Cite (ACL):: Flavio Carvalho, Vanessa Soares, Eduardo Bezerra, and Gustavo Guedes. 2026. ENEM Essay Feedback Using LLM-Augmented Prompts. In Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology, pages 78–85, Cuiabá, Mato Grosso, Brazil. Association for Computational Linguistics.
Cite (Informal):: ENEM Essay Feedback Using LLM-Augmented Prompts (Carvalho et al., STIL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.stil-1.7.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{carvalho-etal-2026-enem,
    title = "{ENEM} Essay Feedback Using {LLM}-Augmented Prompts",
    author = "Carvalho, Flavio  and
      Soares, Vanessa  and
      Bezerra, Eduardo  and
      Guedes, Gustavo",
    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-1.7/",
    doi = "10.5753/stil.2026.26575",
    pages = "78--85",
    abstract = "This paper evaluates automated feedback generation for ENEM Competency 5 by augmenting zero-shot prompts with an Evaluator Term Set (CTA), a term set proposed in this work and extracted from human evaluator comments on Competency 5. We compare CTA-augmented feedback against a zero-shot baseline on 46 essays with human reference feedback using BERTScore F1 and the Wilcoxon signed-rank test. CTA augmentation increases mean BERTScore F1 for both models, with statistically significant improvement in semantic similarity to human feedback for both evaluated models at {\ensuremath{\alpha}} = 0.05."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carvalho-etal-2026-enem">
    <titleInfo>
        <title>ENEM Essay Feedback Using LLM-Augmented Prompts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Flavio</namePart>
        <namePart type="family">Carvalho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vanessa</namePart>
        <namePart type="family">Soares</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eduardo</namePart>
        <namePart type="family">Bezerra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gustavo</namePart>
        <namePart type="family">Guedes</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>This paper evaluates automated feedback generation for ENEM Competency 5 by augmenting zero-shot prompts with an Evaluator Term Set (CTA), a term set proposed in this work and extracted from human evaluator comments on Competency 5. We compare CTA-augmented feedback against a zero-shot baseline on 46 essays with human reference feedback using BERTScore F1 and the Wilcoxon signed-rank test. CTA augmentation increases mean BERTScore F1 for both models, with statistically significant improvement in semantic similarity to human feedback for both evaluated models at \ensuremathα = 0.05.</abstract>
    <identifier type="citekey">carvalho-etal-2026-enem</identifier>
    <identifier type="doi">10.5753/stil.2026.26575</identifier>
    <location>
        <url>https://aclanthology.org/2026.stil-1.7/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>78</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T ENEM Essay Feedback Using LLM-Augmented Prompts
%A Carvalho, Flavio
%A Soares, Vanessa
%A Bezerra, Eduardo
%A Guedes, Gustavo
%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 carvalho-etal-2026-enem
%X This paper evaluates automated feedback generation for ENEM Competency 5 by augmenting zero-shot prompts with an Evaluator Term Set (CTA), a term set proposed in this work and extracted from human evaluator comments on Competency 5. We compare CTA-augmented feedback against a zero-shot baseline on 46 essays with human reference feedback using BERTScore F1 and the Wilcoxon signed-rank test. CTA augmentation increases mean BERTScore F1 for both models, with statistically significant improvement in semantic similarity to human feedback for both evaluated models at \ensuremathα = 0.05.
%R 10.5753/stil.2026.26575
%U https://aclanthology.org/2026.stil-1.7/
%U https://doi.org/10.5753/stil.2026.26575
%P 78-85

Download as File

Markdown (Informal)

[ENEM Essay Feedback Using LLM-Augmented Prompts](https://aclanthology.org/2026.stil-1.7/) (Carvalho et al., STIL 2026)

ENEM Essay Feedback Using LLM-Augmented Prompts (Carvalho et al., STIL 2026)

ACL

Flavio Carvalho, Vanessa Soares, Eduardo Bezerra, and Gustavo Guedes. 2026. ENEM Essay Feedback Using LLM-Augmented Prompts. In Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology, pages 78–85, Cuiabá, Mato Grosso, Brazil. Association for Computational Linguistics.