@inproceedings{khoramfar-etal-2025-permed,
title = "{P}er{M}ed-{MM}: A Multimodal, Multi-Specialty {P}ersian Medical Benchmark for Evaluating Vision Language Models",
author = "Khoramfar, Ali and
Dousti, Mohammad Javad and
Faili, Heshaam",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-short.21/",
pages = "232--241",
ISBN = "979-8-89176-299-2",
abstract = "We present PerMed-MM, the first multimodal benchmark for Persian medical question answering. The dataset comprises 733 expert-authored multiple-choice questions from Iranian National Medical Board Exams, each paired with one to five clinically relevant images, spanning 46 medical specialties and diverse visual modalities. We evaluate five open-source and five proprietary vision language models, and find that reasoning supervision and domain-specific fine-tuning yield performance gains. Our cross-lingual analysis reveals significant unpredictability in translation-based pipelines, motivating the need for benchmarks that support direct, native-language evaluation. Additionally, domain- and modality-level analysis uncovers meaningful variation in model behavior often masked by aggregate metrics. PerMed-MM is publicly available on Hugging Face."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khoramfar-etal-2025-permed">
<titleInfo>
<title>PerMed-MM: A Multimodal, Multi-Specialty Persian Medical Benchmark for Evaluating Vision Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Khoramfar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Javad</namePart>
<namePart type="family">Dousti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heshaam</namePart>
<namePart type="family">Faili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</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">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-299-2</identifier>
</relatedItem>
<abstract>We present PerMed-MM, the first multimodal benchmark for Persian medical question answering. The dataset comprises 733 expert-authored multiple-choice questions from Iranian National Medical Board Exams, each paired with one to five clinically relevant images, spanning 46 medical specialties and diverse visual modalities. We evaluate five open-source and five proprietary vision language models, and find that reasoning supervision and domain-specific fine-tuning yield performance gains. Our cross-lingual analysis reveals significant unpredictability in translation-based pipelines, motivating the need for benchmarks that support direct, native-language evaluation. Additionally, domain- and modality-level analysis uncovers meaningful variation in model behavior often masked by aggregate metrics. PerMed-MM is publicly available on Hugging Face.</abstract>
<identifier type="citekey">khoramfar-etal-2025-permed</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-short.21/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>232</start>
<end>241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PerMed-MM: A Multimodal, Multi-Specialty Persian Medical Benchmark for Evaluating Vision Language Models
%A Khoramfar, Ali
%A Dousti, Mohammad Javad
%A Faili, Heshaam
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-299-2
%F khoramfar-etal-2025-permed
%X We present PerMed-MM, the first multimodal benchmark for Persian medical question answering. The dataset comprises 733 expert-authored multiple-choice questions from Iranian National Medical Board Exams, each paired with one to five clinically relevant images, spanning 46 medical specialties and diverse visual modalities. We evaluate five open-source and five proprietary vision language models, and find that reasoning supervision and domain-specific fine-tuning yield performance gains. Our cross-lingual analysis reveals significant unpredictability in translation-based pipelines, motivating the need for benchmarks that support direct, native-language evaluation. Additionally, domain- and modality-level analysis uncovers meaningful variation in model behavior often masked by aggregate metrics. PerMed-MM is publicly available on Hugging Face.
%U https://aclanthology.org/2025.ijcnlp-short.21/
%P 232-241
Markdown (Informal)
[PerMed-MM: A Multimodal, Multi-Specialty Persian Medical Benchmark for Evaluating Vision Language Models](https://aclanthology.org/2025.ijcnlp-short.21/) (Khoramfar et al., IJCNLP-AACL 2025)
ACL