@inproceedings{zhu-etal-2025-statschartmwp,
title = "{S}tats{C}hart{MWP}: A Dataset for Evaluating Multimodal Mathematical Reasoning Abilities on Math Word Problems with Statistical Charts",
author = "Zhu, Dan and
Liu, Tianqiao and
Liu, Zitao",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.695/",
pages = "12944--12954",
ISBN = "979-8-89176-335-7",
abstract = "Recent advancements in Large Multimodal Models (LMMs) have showcased their impressive capabilities in mathematical reasoning tasks in visual contexts. As a step toward developing AI models to conduct rigorous multi-step multimodal reasoning, we introduce StatsChartMWP, a real-world educational dataset for evaluating visual mathematical reasoning abilities on math word problems (MWPs) with statistical charts. Our dataset contains 8,514 chart-based MWPs, meticulously curated by K-12 educators within real-world teaching scenarios. We provide detailed preprocessing steps and manual annotations to help evaluate state-of-the-art models on StatsChartMWP. Comparing baselines, we find that current models struggle in undertaking meticulous multi-step mathematical reasoning among technical languages, diagrams, tables, and equations. Towards alleviate this gap, we introduce CoTAR, a chain-of-thought (CoT) augmented reasoning solution that fine-tunes the LMMs with solution-oriented CoT-alike reasoning steps. The LMM trained with CoTAR is more effective than current open-source approaches. We conclude by shedding lights on challenges and opportunities in enhancement in LMMs and steer future research and development efforts in the realm of statistical chart comprehension and analysis. The code and data are available at \url{https://github.com/ai4ed/StatsChartMWP}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-statschartmwp">
<titleInfo>
<title>StatsChartMWP: A Dataset for Evaluating Multimodal Mathematical Reasoning Abilities on Math Word Problems with Statistical Charts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianqiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zitao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Recent advancements in Large Multimodal Models (LMMs) have showcased their impressive capabilities in mathematical reasoning tasks in visual contexts. As a step toward developing AI models to conduct rigorous multi-step multimodal reasoning, we introduce StatsChartMWP, a real-world educational dataset for evaluating visual mathematical reasoning abilities on math word problems (MWPs) with statistical charts. Our dataset contains 8,514 chart-based MWPs, meticulously curated by K-12 educators within real-world teaching scenarios. We provide detailed preprocessing steps and manual annotations to help evaluate state-of-the-art models on StatsChartMWP. Comparing baselines, we find that current models struggle in undertaking meticulous multi-step mathematical reasoning among technical languages, diagrams, tables, and equations. Towards alleviate this gap, we introduce CoTAR, a chain-of-thought (CoT) augmented reasoning solution that fine-tunes the LMMs with solution-oriented CoT-alike reasoning steps. The LMM trained with CoTAR is more effective than current open-source approaches. We conclude by shedding lights on challenges and opportunities in enhancement in LMMs and steer future research and development efforts in the realm of statistical chart comprehension and analysis. The code and data are available at https://github.com/ai4ed/StatsChartMWP.</abstract>
<identifier type="citekey">zhu-etal-2025-statschartmwp</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.695/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>12944</start>
<end>12954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StatsChartMWP: A Dataset for Evaluating Multimodal Mathematical Reasoning Abilities on Math Word Problems with Statistical Charts
%A Zhu, Dan
%A Liu, Tianqiao
%A Liu, Zitao
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zhu-etal-2025-statschartmwp
%X Recent advancements in Large Multimodal Models (LMMs) have showcased their impressive capabilities in mathematical reasoning tasks in visual contexts. As a step toward developing AI models to conduct rigorous multi-step multimodal reasoning, we introduce StatsChartMWP, a real-world educational dataset for evaluating visual mathematical reasoning abilities on math word problems (MWPs) with statistical charts. Our dataset contains 8,514 chart-based MWPs, meticulously curated by K-12 educators within real-world teaching scenarios. We provide detailed preprocessing steps and manual annotations to help evaluate state-of-the-art models on StatsChartMWP. Comparing baselines, we find that current models struggle in undertaking meticulous multi-step mathematical reasoning among technical languages, diagrams, tables, and equations. Towards alleviate this gap, we introduce CoTAR, a chain-of-thought (CoT) augmented reasoning solution that fine-tunes the LMMs with solution-oriented CoT-alike reasoning steps. The LMM trained with CoTAR is more effective than current open-source approaches. We conclude by shedding lights on challenges and opportunities in enhancement in LMMs and steer future research and development efforts in the realm of statistical chart comprehension and analysis. The code and data are available at https://github.com/ai4ed/StatsChartMWP.
%U https://aclanthology.org/2025.findings-emnlp.695/
%P 12944-12954
Markdown (Informal)
[StatsChartMWP: A Dataset for Evaluating Multimodal Mathematical Reasoning Abilities on Math Word Problems with Statistical Charts](https://aclanthology.org/2025.findings-emnlp.695/) (Zhu et al., Findings 2025)
ACL