@inproceedings{turek-etal-2026-multimodal,
title = "Can Multimodal Large Language Models Identify Thematic Maps in Scientific Articles?",
author = "Turek, Tomas and
Nguyen, Vincent and
Singh, Dhirendra and
Karimi, Sarvnaz and
Zhang, Xiuzhen",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.17/",
pages = "231--245",
ISBN = "979-8-89176-465-1",
abstract = "Information seeking systems have yet to access multimodal information about thematic maps in scientific literature. Thematic maps are images of geographical maps showing themes of information and are crucial for understanding the impact of climate on natural resources. Although Multimodal Large Language Models (MLLMs) are applied in different applications, their effectiveness in identifying thematic maps is not explored. We address this gap by evaluating some of the state-of-the-art MLLMs to (1) classify thematic maps using different visual and textual contexts; (2) explain their predictions and uncover their sources of bias using {\_}attribute discovery{\_}; and (3) assist humans with the annotation of thematic maps in the scientific literature. We release a new public dataset (https://github.com/tomtx/cp-thematic-maps) and use it to show that MLLMs that were investigated in our study have room for improvement. We observe that MLLMs can be biased toward visual attributes of thematic maps (graphical indicators). The best classification result is an 80{\%} strict F1 score by the Grok 4.3 model, which can fluctuate between 76{\%} and 84{\%} due to classification bias. Overall, we consistently find that the input of images with captions and examples of the correct answers yields substantial gains in task performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turek-etal-2026-multimodal">
<titleInfo>
<title>Can Multimodal Large Language Models Identify Thematic Maps in Scientific Articles?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomas</namePart>
<namePart type="family">Turek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarvnaz</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuzhen</namePart>
<namePart type="family">Zhang</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 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Usmanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>Information seeking systems have yet to access multimodal information about thematic maps in scientific literature. Thematic maps are images of geographical maps showing themes of information and are crucial for understanding the impact of climate on natural resources. Although Multimodal Large Language Models (MLLMs) are applied in different applications, their effectiveness in identifying thematic maps is not explored. We address this gap by evaluating some of the state-of-the-art MLLMs to (1) classify thematic maps using different visual and textual contexts; (2) explain their predictions and uncover their sources of bias using _attribute discovery_; and (3) assist humans with the annotation of thematic maps in the scientific literature. We release a new public dataset (https://github.com/tomtx/cp-thematic-maps) and use it to show that MLLMs that were investigated in our study have room for improvement. We observe that MLLMs can be biased toward visual attributes of thematic maps (graphical indicators). The best classification result is an 80% strict F1 score by the Grok 4.3 model, which can fluctuate between 76% and 84% due to classification bias. Overall, we consistently find that the input of images with captions and examples of the correct answers yields substantial gains in task performance.</abstract>
<identifier type="citekey">turek-etal-2026-multimodal</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.17/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>231</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Multimodal Large Language Models Identify Thematic Maps in Scientific Articles?
%A Turek, Tomas
%A Nguyen, Vincent
%A Singh, Dhirendra
%A Karimi, Sarvnaz
%A Zhang, Xiuzhen
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F turek-etal-2026-multimodal
%X Information seeking systems have yet to access multimodal information about thematic maps in scientific literature. Thematic maps are images of geographical maps showing themes of information and are crucial for understanding the impact of climate on natural resources. Although Multimodal Large Language Models (MLLMs) are applied in different applications, their effectiveness in identifying thematic maps is not explored. We address this gap by evaluating some of the state-of-the-art MLLMs to (1) classify thematic maps using different visual and textual contexts; (2) explain their predictions and uncover their sources of bias using _attribute discovery_; and (3) assist humans with the annotation of thematic maps in the scientific literature. We release a new public dataset (https://github.com/tomtx/cp-thematic-maps) and use it to show that MLLMs that were investigated in our study have room for improvement. We observe that MLLMs can be biased toward visual attributes of thematic maps (graphical indicators). The best classification result is an 80% strict F1 score by the Grok 4.3 model, which can fluctuate between 76% and 84% due to classification bias. Overall, we consistently find that the input of images with captions and examples of the correct answers yields substantial gains in task performance.
%U https://aclanthology.org/2026.climatenlp-1.17/
%P 231-245
Markdown (Informal)
[Can Multimodal Large Language Models Identify Thematic Maps in Scientific Articles?](https://aclanthology.org/2026.climatenlp-1.17/) (Turek et al., ClimateNLP 2026)
ACL