@inproceedings{cosma-etal-2025-romath,
title = "{R}o{M}ath: A Mathematical Reasoning Benchmark in {R}omanian",
author = "Cosma, Adrian and
Bucur, Ana-Maria and
Radoi, Emilian",
editor = "Valentino, Marco and
Ferreira, Deborah and
Thayaparan, Mokanarangan and
Ranaldi, Leonardo and
Freitas, Andre",
booktitle = "Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mathnlp-main.7/",
pages = "95--111",
ISBN = "979-8-89176-348-7",
abstract = "Mathematics has long been conveyed through natural language, primarily for human understanding. With the rise of mechanized mathematics and proof assistants, there is a growing need to understand informal mathematical text, yet most existing benchmarks focus solely on English, overlooking other languages. This paper introduces RoMath, a Romanian mathematical reasoning benchmark suite comprising three subsets: Baccalaureate, Competitions and Synthetic, which cover a range of mathematical domains and difficulty levels, aiming to improve non-English language models and promote multilingual AI development. By focusing on Romanian, a low-resource language with unique linguistic features, RoMath addresses the limitations of Anglo-centric models and emphasizes the need for dedicated resources beyond simple automatic translation. We benchmark several open-weight language models, highlighting the importance of creating resources for underrepresented languages. The code and datasets are available for research purposes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cosma-etal-2025-romath">
<titleInfo>
<title>RoMath: A Mathematical Reasoning Benchmark in Romanian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Cosma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana-Maria</namePart>
<namePart type="family">Bucur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emilian</namePart>
<namePart type="family">Radoi</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>Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deborah</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mokanarangan</namePart>
<namePart type="family">Thayaparan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Freitas</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">979-8-89176-348-7</identifier>
</relatedItem>
<abstract>Mathematics has long been conveyed through natural language, primarily for human understanding. With the rise of mechanized mathematics and proof assistants, there is a growing need to understand informal mathematical text, yet most existing benchmarks focus solely on English, overlooking other languages. This paper introduces RoMath, a Romanian mathematical reasoning benchmark suite comprising three subsets: Baccalaureate, Competitions and Synthetic, which cover a range of mathematical domains and difficulty levels, aiming to improve non-English language models and promote multilingual AI development. By focusing on Romanian, a low-resource language with unique linguistic features, RoMath addresses the limitations of Anglo-centric models and emphasizes the need for dedicated resources beyond simple automatic translation. We benchmark several open-weight language models, highlighting the importance of creating resources for underrepresented languages. The code and datasets are available for research purposes.</abstract>
<identifier type="citekey">cosma-etal-2025-romath</identifier>
<location>
<url>https://aclanthology.org/2025.mathnlp-main.7/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>95</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoMath: A Mathematical Reasoning Benchmark in Romanian
%A Cosma, Adrian
%A Bucur, Ana-Maria
%A Radoi, Emilian
%Y Valentino, Marco
%Y Ferreira, Deborah
%Y Thayaparan, Mokanarangan
%Y Ranaldi, Leonardo
%Y Freitas, Andre
%S Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-348-7
%F cosma-etal-2025-romath
%X Mathematics has long been conveyed through natural language, primarily for human understanding. With the rise of mechanized mathematics and proof assistants, there is a growing need to understand informal mathematical text, yet most existing benchmarks focus solely on English, overlooking other languages. This paper introduces RoMath, a Romanian mathematical reasoning benchmark suite comprising three subsets: Baccalaureate, Competitions and Synthetic, which cover a range of mathematical domains and difficulty levels, aiming to improve non-English language models and promote multilingual AI development. By focusing on Romanian, a low-resource language with unique linguistic features, RoMath addresses the limitations of Anglo-centric models and emphasizes the need for dedicated resources beyond simple automatic translation. We benchmark several open-weight language models, highlighting the importance of creating resources for underrepresented languages. The code and datasets are available for research purposes.
%U https://aclanthology.org/2025.mathnlp-main.7/
%P 95-111
Markdown (Informal)
[RoMath: A Mathematical Reasoning Benchmark in Romanian](https://aclanthology.org/2025.mathnlp-main.7/) (Cosma et al., MathNLP 2025)
ACL
- Adrian Cosma, Ana-Maria Bucur, and Emilian Radoi. 2025. RoMath: A Mathematical Reasoning Benchmark in Romanian. In Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025), pages 95–111, Suzhou, China. Association for Computational Linguistics.