<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-graf-2025-mathematical">
    <titleInfo>
        <title>Mathematical Computation and Reasoning Errors by Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edith</namePart>
        <namePart type="family">Graf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-10</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">979-8-218-84228-4</identifier>
    </relatedItem>
    <abstract>We evaluate four LLMs (GPT-4o, o1, DeepSeek-V3, DeepSeek-R1) on purposely challenging arithmetic, algebra, and number-theory items. Coding final answers and step-level solutions correctness reveals performance gaps, improvement paths, and how accurate LLMs can strengthen mathematics assessment and instruction.</abstract>
    <identifier type="citekey">zhang-graf-2025-mathematical</identifier>
    <location>
        <url>https://aclanthology.org/2025.aimecon-main.45/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>417</start>
            <end>424</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mathematical Computation and Reasoning Errors by Large Language Models
%A Zhang, Liang
%A Graf, Edith
%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 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F zhang-graf-2025-mathematical
%X We evaluate four LLMs (GPT-4o, o1, DeepSeek-V3, DeepSeek-R1) on purposely challenging arithmetic, algebra, and number-theory items. Coding final answers and step-level solutions correctness reveals performance gaps, improvement paths, and how accurate LLMs can strengthen mathematics assessment and instruction.
%U https://aclanthology.org/2025.aimecon-main.45/
%P 417-424

Markdown (Informal)

[Mathematical Computation and Reasoning Errors by Large Language Models](https://aclanthology.org/2025.aimecon-main.45/) (Zhang & Graf, AIME-Con 2025)

• Mathematical Computation and Reasoning Errors by Large Language Models (Zhang & Graf, AIME-Con 2025)

ACL

• Liang Zhang and Edith Graf. 2025. Mathematical Computation and Reasoning Errors by Large Language Models. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 417–424, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).