@inproceedings{galarnyk-etal-2025-confready,
title = "{C}onf{R}eady: A {RAG} based Assistant and Dataset for Conference Checklist Responses",
author = "Galarnyk, Michael and
Routu, Rutwik and
Kannan, Vidhyakshaya and
Bheda, Kosha and
Banerjee, Prasun and
Shah, Agam and
Chava, Sudheer",
editor = {Habernal, Ivan and
Schulam, Peter and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-demos.49/",
pages = "667--677",
ISBN = "979-8-89176-334-0",
abstract = "The ARR Responsible NLP Research checklist website states that the ``checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility.'' Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering a checklist before submission can favorably impact the writing of a research paper. However, previous research has shown that self-reported checklist responses don{'}t always accurately represent papers. In this work, we introduce ConfReady, a retrieval-augmented generation (RAG) application that can be used to empower authors to reflect on their work and assist authors with conference checklists. To evaluate checklist assistants, we curate a dataset of 1,975 ACL checklist responses, analyze problems in human answers, and benchmark RAG and Large Language Model (LM) based systems on an evaluation subset. Our code is released under the AGPL-3.0 license on GitHub, with documentation covering the user interface and PyPI package."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galarnyk-etal-2025-confready">
<titleInfo>
<title>ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Galarnyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rutwik</namePart>
<namePart type="family">Routu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhyakshaya</namePart>
<namePart type="family">Kannan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosha</namePart>
<namePart type="family">Bheda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasun</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agam</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudheer</namePart>
<namePart type="family">Chava</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Habernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Schulam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</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">979-8-89176-334-0</identifier>
</relatedItem>
<abstract>The ARR Responsible NLP Research checklist website states that the “checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility.” Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering a checklist before submission can favorably impact the writing of a research paper. However, previous research has shown that self-reported checklist responses don’t always accurately represent papers. In this work, we introduce ConfReady, a retrieval-augmented generation (RAG) application that can be used to empower authors to reflect on their work and assist authors with conference checklists. To evaluate checklist assistants, we curate a dataset of 1,975 ACL checklist responses, analyze problems in human answers, and benchmark RAG and Large Language Model (LM) based systems on an evaluation subset. Our code is released under the AGPL-3.0 license on GitHub, with documentation covering the user interface and PyPI package.</abstract>
<identifier type="citekey">galarnyk-etal-2025-confready</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-demos.49/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>667</start>
<end>677</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses
%A Galarnyk, Michael
%A Routu, Rutwik
%A Kannan, Vidhyakshaya
%A Bheda, Kosha
%A Banerjee, Prasun
%A Shah, Agam
%A Chava, Sudheer
%Y Habernal, Ivan
%Y Schulam, Peter
%Y Tiedemann, Jörg
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-334-0
%F galarnyk-etal-2025-confready
%X The ARR Responsible NLP Research checklist website states that the “checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility.” Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering a checklist before submission can favorably impact the writing of a research paper. However, previous research has shown that self-reported checklist responses don’t always accurately represent papers. In this work, we introduce ConfReady, a retrieval-augmented generation (RAG) application that can be used to empower authors to reflect on their work and assist authors with conference checklists. To evaluate checklist assistants, we curate a dataset of 1,975 ACL checklist responses, analyze problems in human answers, and benchmark RAG and Large Language Model (LM) based systems on an evaluation subset. Our code is released under the AGPL-3.0 license on GitHub, with documentation covering the user interface and PyPI package.
%U https://aclanthology.org/2025.emnlp-demos.49/
%P 667-677
Markdown (Informal)
[ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses](https://aclanthology.org/2025.emnlp-demos.49/) (Galarnyk et al., EMNLP 2025)
ACL