@inproceedings{al-azher-etal-2025-bagels,
title = "{BAGELS}: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text",
author = "Al Azher, Ibrahim and
Mokarrama, Miftahul Jannat and
Guo, Zhishuai and
Choudhury, Sagnik Ray and
Alhoori, Hamed",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1050/",
doi = "10.18653/v1/2025.findings-emnlp.1050",
pages = "19279--19294",
ISBN = "979-8-89176-335-7",
abstract = "In scientific research, ``limitations'' refer to the shortcomings, constraints, or weaknesses of a study. A transparent reporting of such limitations can enhance the quality and reproducibility of research and improve public trust in science. However, authors often underreport limitations in their papers and rely on hedging strategies to meet editorial requirements at the expense of readers' clarity and confidence. This tendency, combined with the surge in scientific publications, has created a pressing need for automated approaches to extract and generate limitations from scholarly papers. To address this need, we present a full architecture for computational analysis of research limitations. Specifically, we (1) create a dataset of limitations from ACL, NeurIPS, and PeerJ papers by extracting them from the text and supplementing them with external reviews; (2) we propose methods to automatically generate limitations using a novel Retrieval Augmented Generation (RAG) technique; (3) we design a fine-grained evaluation framework for generated limitations, along with a meta-evaluation of these techniques. Code and datasets are available at: Code: \url{https://github.com/IbrahimAlAzhar/BAGELS_Limitation_Gen}Dataset: \url{https://huggingface.co/datasets/IbrahimAlAzhar/limitation-generation-dataset-bagels}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-azher-etal-2025-bagels">
<titleInfo>
<title>BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Al Azher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miftahul</namePart>
<namePart type="given">Jannat</namePart>
<namePart type="family">Mokarrama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhishuai</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sagnik</namePart>
<namePart type="given">Ray</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamed</namePart>
<namePart type="family">Alhoori</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>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</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">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>In scientific research, “limitations” refer to the shortcomings, constraints, or weaknesses of a study. A transparent reporting of such limitations can enhance the quality and reproducibility of research and improve public trust in science. However, authors often underreport limitations in their papers and rely on hedging strategies to meet editorial requirements at the expense of readers’ clarity and confidence. This tendency, combined with the surge in scientific publications, has created a pressing need for automated approaches to extract and generate limitations from scholarly papers. To address this need, we present a full architecture for computational analysis of research limitations. Specifically, we (1) create a dataset of limitations from ACL, NeurIPS, and PeerJ papers by extracting them from the text and supplementing them with external reviews; (2) we propose methods to automatically generate limitations using a novel Retrieval Augmented Generation (RAG) technique; (3) we design a fine-grained evaluation framework for generated limitations, along with a meta-evaluation of these techniques. Code and datasets are available at: Code: https://github.com/IbrahimAlAzhar/BAGELS_Limitation_GenDataset: https://huggingface.co/datasets/IbrahimAlAzhar/limitation-generation-dataset-bagels</abstract>
<identifier type="citekey">al-azher-etal-2025-bagels</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.1050</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1050/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>19279</start>
<end>19294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text
%A Al Azher, Ibrahim
%A Mokarrama, Miftahul Jannat
%A Guo, Zhishuai
%A Choudhury, Sagnik Ray
%A Alhoori, Hamed
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F al-azher-etal-2025-bagels
%X In scientific research, “limitations” refer to the shortcomings, constraints, or weaknesses of a study. A transparent reporting of such limitations can enhance the quality and reproducibility of research and improve public trust in science. However, authors often underreport limitations in their papers and rely on hedging strategies to meet editorial requirements at the expense of readers’ clarity and confidence. This tendency, combined with the surge in scientific publications, has created a pressing need for automated approaches to extract and generate limitations from scholarly papers. To address this need, we present a full architecture for computational analysis of research limitations. Specifically, we (1) create a dataset of limitations from ACL, NeurIPS, and PeerJ papers by extracting them from the text and supplementing them with external reviews; (2) we propose methods to automatically generate limitations using a novel Retrieval Augmented Generation (RAG) technique; (3) we design a fine-grained evaluation framework for generated limitations, along with a meta-evaluation of these techniques. Code and datasets are available at: Code: https://github.com/IbrahimAlAzhar/BAGELS_Limitation_GenDataset: https://huggingface.co/datasets/IbrahimAlAzhar/limitation-generation-dataset-bagels
%R 10.18653/v1/2025.findings-emnlp.1050
%U https://aclanthology.org/2025.findings-emnlp.1050/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1050
%P 19279-19294
Markdown (Informal)
[BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text](https://aclanthology.org/2025.findings-emnlp.1050/) (Al Azher et al., Findings 2025)
ACL