@inproceedings{bolucu-etal-2026-scientific,
title = "Scientific Table Generation: Structured Information Extraction from Scientific Literature",
author = {B{\"o}l{\"u}c{\"u}, Necva and
Yang, Huichen and
Timmer, Roelien C. and
Wan, Stephen and
Jin, Brian and
Lee, Changhyun and
Duenser, Andreas and
Irons, Jessica},
editor = "Accomazzi, Alberto and
Ghosal, Tirthankar and
Grezes, Felix and
Lockhart, Kelly and
Alkan, Atilla Kaan",
booktitle = "Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wasp-1.25/",
pages = "224--246",
ISBN = "979-8-89176-456-9",
abstract = "We introduce \textit{Scientific Table Generation (STG)}, the task of extracting information from scientific documents to populate a table. We argue that STG can serve as a unifying task for structured knowledge extraction from scientific literature. To support this goal, we present the first multi-disciplinary benchmark for STG with predefined schemas and multi-record extraction, covering six scientific domains and comprising 20 datasets unified under our proposed formulation. We detail the benchmark{'}s construction, including dataset composition, and introduce an \textit{STG evaluation protocol}. We analyse the results of zero-shot large language model (LLM) and vision-language model (VLM) pipelines with typical document processing AI methods for the STG task. In doing so, we identify key challenges of the STG task and propose a set of open challenges, including multimodality, table and figure understanding, normalisation of data, and treatment of reported quantities. All code and data accompanying this work are publicly available at[This repository will save researchers significant time. Instead of manually searching for 20 different datasets, researchers can use our repository to download all datasets directly, as a download link is provided for each paper. In addition, researchers can use our evaluation framework, which streamlines the process and improves overall efficiency.]: \url{https://github.com/bolucunecva/table_generation}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bolucu-etal-2026-scientific">
<titleInfo>
<title>Scientific Table Generation: Structured Information Extraction from Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Necva</namePart>
<namePart type="family">Bölücü</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huichen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roelien</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Timmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changhyun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Duenser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Irons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Lockhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atilla</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Alkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-456-9</identifier>
</relatedItem>
<abstract>We introduce Scientific Table Generation (STG), the task of extracting information from scientific documents to populate a table. We argue that STG can serve as a unifying task for structured knowledge extraction from scientific literature. To support this goal, we present the first multi-disciplinary benchmark for STG with predefined schemas and multi-record extraction, covering six scientific domains and comprising 20 datasets unified under our proposed formulation. We detail the benchmark’s construction, including dataset composition, and introduce an STG evaluation protocol. We analyse the results of zero-shot large language model (LLM) and vision-language model (VLM) pipelines with typical document processing AI methods for the STG task. In doing so, we identify key challenges of the STG task and propose a set of open challenges, including multimodality, table and figure understanding, normalisation of data, and treatment of reported quantities. All code and data accompanying this work are publicly available at[This repository will save researchers significant time. Instead of manually searching for 20 different datasets, researchers can use our repository to download all datasets directly, as a download link is provided for each paper. In addition, researchers can use our evaluation framework, which streamlines the process and improves overall efficiency.]: https://github.com/bolucunecva/table_generation</abstract>
<identifier type="citekey">bolucu-etal-2026-scientific</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.25/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>224</start>
<end>246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scientific Table Generation: Structured Information Extraction from Scientific Literature
%A Bölücü, Necva
%A Yang, Huichen
%A Timmer, Roelien C.
%A Wan, Stephen
%A Jin, Brian
%A Lee, Changhyun
%A Duenser, Andreas
%A Irons, Jessica
%Y Accomazzi, Alberto
%Y Ghosal, Tirthankar
%Y Grezes, Felix
%Y Lockhart, Kelly
%Y Alkan, Atilla Kaan
%S Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-456-9
%F bolucu-etal-2026-scientific
%X We introduce Scientific Table Generation (STG), the task of extracting information from scientific documents to populate a table. We argue that STG can serve as a unifying task for structured knowledge extraction from scientific literature. To support this goal, we present the first multi-disciplinary benchmark for STG with predefined schemas and multi-record extraction, covering six scientific domains and comprising 20 datasets unified under our proposed formulation. We detail the benchmark’s construction, including dataset composition, and introduce an STG evaluation protocol. We analyse the results of zero-shot large language model (LLM) and vision-language model (VLM) pipelines with typical document processing AI methods for the STG task. In doing so, we identify key challenges of the STG task and propose a set of open challenges, including multimodality, table and figure understanding, normalisation of data, and treatment of reported quantities. All code and data accompanying this work are publicly available at[This repository will save researchers significant time. Instead of manually searching for 20 different datasets, researchers can use our repository to download all datasets directly, as a download link is provided for each paper. In addition, researchers can use our evaluation framework, which streamlines the process and improves overall efficiency.]: https://github.com/bolucunecva/table_generation
%U https://aclanthology.org/2026.wasp-1.25/
%P 224-246
Markdown (Informal)
[Scientific Table Generation: Structured Information Extraction from Scientific Literature](https://aclanthology.org/2026.wasp-1.25/) (Bölücü et al., WASP 2026)
ACL
- Necva Bölücü, Huichen Yang, Roelien C. Timmer, Stephen Wan, Brian Jin, Changhyun Lee, Andreas Duenser, and Jessica Irons. 2026. Scientific Table Generation: Structured Information Extraction from Scientific Literature. In Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications, pages 224–246, Hengqin, Zhuhai, China. Association for Computational Linguistics.