Can Small Language Models Teach Math Through Socratic Dialogue?

Dizhi Zhang; Mengchen Li; Zichen Wang; Ziqiao Zeng; Shruti Mehta; Talita de Paula Cypriano de Souza; Seiji Isotani

Can Small Language Models Teach Math Through Socratic Dialogue?

Dizhi Zhang, Mengchen Li, Zichen Wang, Ziqiao Zeng, Shruti Mehta, Talita de Paula Cypriano de Souza, Seiji Isotani

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 study evaluates whether three locally deployed small language models (LLaMA-3.2-1B, Qwen-2.5-0.5B, and Gemma-3-1B) can implement Socratic tutoring in Grade 6–8 mathematics. Using a rubric-based protocol across 72 sessions, results show that all models struggled to sustain guided inquiry, with Gemma performing best overall.

Anthology ID:: 2026.aimecon-main.67
Volume:: Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
Month:: October
Year:: 2026
Address:: Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
Editors:: Joshua Wilson, Christopher Ormerod, Magdalen Beiting-Parrish
Venue:: AIME-Con
SIG:
Publisher:: National Council on Measurement in Education (NCME)
Note:
Pages:: 599–605
Language:
URL:: https://aclanthology.org/2026.aimecon-main.67/
DOI:
Bibkey:
Cite (ACL):: Dizhi Zhang, Mengchen Li, Zichen Wang, Ziqiao Zeng, Shruti Mehta, Talita de Paula Cypriano de Souza, and Seiji Isotani. 2026. Can Small Language Models Teach Math Through Socratic Dialogue?. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 599–605, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).
Cite (Informal):: Can Small Language Models Teach Math Through Socratic Dialogue? (Zhang et al., AIME-Con 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.aimecon-main.67.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zhang-etal-2026-small,
    title = "Can Small Language Models Teach Math Through Socratic Dialogue?",
    author = "Zhang, Dizhi  and
      Li, Mengchen  and
      Wang, Zichen  and
      Zeng, Ziqiao  and
      Mehta, Shruti  and
      de Souza, Talita de Paula Cypriano  and
      Isotani, Seiji",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting-Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Full Papers",
    month = oct,
    year = "2026",
    address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://aclanthology.org/2026.aimecon-main.67/",
    pages = "599--605",
    ISBN = "979-8-9983004-0-0",
    abstract = "This study evaluates whether three locally deployed small language models (LLaMA-3.2-1B, Qwen-2.5-0.5B, and Gemma-3-1B) can implement Socratic tutoring in Grade 6{--}8 mathematics. Using a rubric-based protocol across 72 sessions, results show that all models struggled to sustain guided inquiry, with Gemma performing best overall."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-small">
    <titleInfo>
        <title>Can Small Language Models Teach Math Through Socratic Dialogue?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dizhi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mengchen</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zichen</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziqiao</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shruti</namePart>
        <namePart type="family">Mehta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Talita</namePart>
        <namePart type="given">de</namePart>
        <namePart type="given">Paula</namePart>
        <namePart type="given">Cypriano</namePart>
        <namePart type="family">de Souza</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seiji</namePart>
        <namePart type="family">Isotani</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 Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting-Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-9983004-0-0</identifier>
    </relatedItem>
    <abstract>This study evaluates whether three locally deployed small language models (LLaMA-3.2-1B, Qwen-2.5-0.5B, and Gemma-3-1B) can implement Socratic tutoring in Grade 6–8 mathematics. Using a rubric-based protocol across 72 sessions, results show that all models struggled to sustain guided inquiry, with Gemma performing best overall.</abstract>
    <identifier type="citekey">zhang-etal-2026-small</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-main.67/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>599</start>
            <end>605</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Can Small Language Models Teach Math Through Socratic Dialogue?
%A Zhang, Dizhi
%A Li, Mengchen
%A Wang, Zichen
%A Zeng, Ziqiao
%A Mehta, Shruti
%A de Souza, Talita de Paula Cypriano
%A Isotani, Seiji
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-0-0
%F zhang-etal-2026-small
%X This study evaluates whether three locally deployed small language models (LLaMA-3.2-1B, Qwen-2.5-0.5B, and Gemma-3-1B) can implement Socratic tutoring in Grade 6–8 mathematics. Using a rubric-based protocol across 72 sessions, results show that all models struggled to sustain guided inquiry, with Gemma performing best overall.
%U https://aclanthology.org/2026.aimecon-main.67/
%P 599-605

Download as File

Markdown (Informal)

[Can Small Language Models Teach Math Through Socratic Dialogue?](https://aclanthology.org/2026.aimecon-main.67/) (Zhang et al., AIME-Con 2026)

Can Small Language Models Teach Math Through Socratic Dialogue? (Zhang et al., AIME-Con 2026)

ACL

Dizhi Zhang, Mengchen Li, Zichen Wang, Ziqiao Zeng, Shruti Mehta, Talita de Paula Cypriano de Souza, and Seiji Isotani. 2026. Can Small Language Models Teach Math Through Socratic Dialogue?. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 599–605, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).