@inproceedings{li-etal-2024-m3sciqa,
title = "{M}3{S}ci{QA}: A Multi-Modal Multi-Document Scientific {QA} Benchmark for Evaluating Foundation Models",
author = "Li, Chuhan and
Shangguan, Ziyao and
Zhao, Yilun and
Li, Deyuan and
Liu, Yixin and
Cohan, Arman",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.904",
pages = "15419--15446",
abstract = "Existing evaluation benchmarks for foundation models in understanding scientific literature predominantly focus on single-document, text-only tasks. Such benchmarks often do not adequately represent the complexity of research workflows, which typically also involve interpreting non-textual data, such as figures and tables, and gathering information across multiple documents and related literature. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3Sci QA consists of 1452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster represents a primary paper along with all its cited documents, mirroring the workflow of comprehending a single paper by requiring multi-modal and multi-document data. With M3SciQA, we conduct a comprehensive evaluation of 18 frontier foundation models. Our results indicate that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents. Additionally, we explore the implications of these findings for the future advancement of applying foundation models in multi-modal scientific literature analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-m3sciqa">
<titleInfo>
<title>M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuhan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyao</namePart>
<namePart type="family">Shangguan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing evaluation benchmarks for foundation models in understanding scientific literature predominantly focus on single-document, text-only tasks. Such benchmarks often do not adequately represent the complexity of research workflows, which typically also involve interpreting non-textual data, such as figures and tables, and gathering information across multiple documents and related literature. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3Sci QA consists of 1452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster represents a primary paper along with all its cited documents, mirroring the workflow of comprehending a single paper by requiring multi-modal and multi-document data. With M3SciQA, we conduct a comprehensive evaluation of 18 frontier foundation models. Our results indicate that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents. Additionally, we explore the implications of these findings for the future advancement of applying foundation models in multi-modal scientific literature analysis.</abstract>
<identifier type="citekey">li-etal-2024-m3sciqa</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.904</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15419</start>
<end>15446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models
%A Li, Chuhan
%A Shangguan, Ziyao
%A Zhao, Yilun
%A Li, Deyuan
%A Liu, Yixin
%A Cohan, Arman
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F li-etal-2024-m3sciqa
%X Existing evaluation benchmarks for foundation models in understanding scientific literature predominantly focus on single-document, text-only tasks. Such benchmarks often do not adequately represent the complexity of research workflows, which typically also involve interpreting non-textual data, such as figures and tables, and gathering information across multiple documents and related literature. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3Sci QA consists of 1452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster represents a primary paper along with all its cited documents, mirroring the workflow of comprehending a single paper by requiring multi-modal and multi-document data. With M3SciQA, we conduct a comprehensive evaluation of 18 frontier foundation models. Our results indicate that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents. Additionally, we explore the implications of these findings for the future advancement of applying foundation models in multi-modal scientific literature analysis.
%U https://aclanthology.org/2024.findings-emnlp.904
%P 15419-15446
Markdown (Informal)
[M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models](https://aclanthology.org/2024.findings-emnlp.904) (Li et al., Findings 2024)
ACL