@inproceedings{aubert-beduchaud-etal-2025-acl,
title = "{ACL}-rlg: A Dataset for Reading List Generation",
author = "Aubert-B{\'e}duchaud, Julien and
Boudin, Florian and
Daille, B{\'e}atrice and
Dufour, Richard",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.327/",
pages = "4910--4919",
abstract = "Familiarizing oneself with a new scientific field and its existing literature can be daunting due to the large amount of available articles. Curated lists of academic references, or reading lists, compiled by experts, offer a structured way to gain a comprehensive overview of a domain or a specific scientific challenge. In this work, we introduce ACL-rlg, the largest open expert-annotated reading list dataset. We also provide multiple baselines for evaluating reading list generation and formally define it as a retrieval task. Our qualitative study highlights that traditional scholarly search engines and indexing methods perform poorly on this task, and GPT-4o, despite showing better results, exhibits signs of potential data contamination."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aubert-beduchaud-etal-2025-acl">
<titleInfo>
<title>ACL-rlg: A Dataset for Reading List Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Aubert-Béduchaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Boudin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Béatrice</namePart>
<namePart type="family">Daille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Dufour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Familiarizing oneself with a new scientific field and its existing literature can be daunting due to the large amount of available articles. Curated lists of academic references, or reading lists, compiled by experts, offer a structured way to gain a comprehensive overview of a domain or a specific scientific challenge. In this work, we introduce ACL-rlg, the largest open expert-annotated reading list dataset. We also provide multiple baselines for evaluating reading list generation and formally define it as a retrieval task. Our qualitative study highlights that traditional scholarly search engines and indexing methods perform poorly on this task, and GPT-4o, despite showing better results, exhibits signs of potential data contamination.</abstract>
<identifier type="citekey">aubert-beduchaud-etal-2025-acl</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.327/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>4910</start>
<end>4919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ACL-rlg: A Dataset for Reading List Generation
%A Aubert-Béduchaud, Julien
%A Boudin, Florian
%A Daille, Béatrice
%A Dufour, Richard
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F aubert-beduchaud-etal-2025-acl
%X Familiarizing oneself with a new scientific field and its existing literature can be daunting due to the large amount of available articles. Curated lists of academic references, or reading lists, compiled by experts, offer a structured way to gain a comprehensive overview of a domain or a specific scientific challenge. In this work, we introduce ACL-rlg, the largest open expert-annotated reading list dataset. We also provide multiple baselines for evaluating reading list generation and formally define it as a retrieval task. Our qualitative study highlights that traditional scholarly search engines and indexing methods perform poorly on this task, and GPT-4o, despite showing better results, exhibits signs of potential data contamination.
%U https://aclanthology.org/2025.coling-main.327/
%P 4910-4919
Markdown (Informal)
[ACL-rlg: A Dataset for Reading List Generation](https://aclanthology.org/2025.coling-main.327/) (Aubert-Béduchaud et al., COLING 2025)
ACL
- Julien Aubert-Béduchaud, Florian Boudin, Béatrice Daille, and Richard Dufour. 2025. ACL-rlg: A Dataset for Reading List Generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4910–4919, Abu Dhabi, UAE. Association for Computational Linguistics.