@inproceedings{tonja-etal-2026-arr,
title = "{ARR}-{D}v2: New Data from {ACL} Rolling Review and its Potential to Improve Reviewing in the {ACL} Community",
author = "Tonja, Atnafu Lambebo and
Lu, Sheng and
Dycke, Nils and
Hovy, Dirk and
Dercksen, Koen and
Qu, Lizhen and
Zhu, Xiaodan and
Solorio, Thamar and
Gurevych, Iryna and
Mieskes, Margot",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.17/",
pages = "333--350",
ISBN = "979-8-89176-439-2",
abstract = "We present a new dataset to support AI-assisted and human studies of the peer reviewing process, based on the ARR Open Review Platform. Unlike previous similar data collections, ours, ARR-Dv2, not only contains the reviews but also author-reviewer discussions (aka rebuttal phase) and meta-reviews. We present statistical analyses of the data with respect to the overall score and the correlations among the overall score, confidence, and soundness scores. Additionally, we extend the task of Review Score Prediction also to include rebuttal data and analyze its effect on score prediction. Finally, we introduce a new task, Meta Review Score Prediction, based on a set of up to three reviews rather than a single review. Our initial results in a zero-shot setting indicate that the rebuttal data adds valuable information to the score prediction and enables reliable predictions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tonja-etal-2026-arr">
<titleInfo>
<title>ARR-Dv2: New Data from ACL Rolling Review and its Potential to Improve Reviewing in the ACL Community</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Dycke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koen</namePart>
<namePart type="family">Dercksen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Mieskes</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 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>We present a new dataset to support AI-assisted and human studies of the peer reviewing process, based on the ARR Open Review Platform. Unlike previous similar data collections, ours, ARR-Dv2, not only contains the reviews but also author-reviewer discussions (aka rebuttal phase) and meta-reviews. We present statistical analyses of the data with respect to the overall score and the correlations among the overall score, confidence, and soundness scores. Additionally, we extend the task of Review Score Prediction also to include rebuttal data and analyze its effect on score prediction. Finally, we introduce a new task, Meta Review Score Prediction, based on a set of up to three reviews rather than a single review. Our initial results in a zero-shot setting indicate that the rebuttal data adds valuable information to the score prediction and enables reliable predictions.</abstract>
<identifier type="citekey">tonja-etal-2026-arr</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.17/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>333</start>
<end>350</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARR-Dv2: New Data from ACL Rolling Review and its Potential to Improve Reviewing in the ACL Community
%A Tonja, Atnafu Lambebo
%A Lu, Sheng
%A Dycke, Nils
%A Hovy, Dirk
%A Dercksen, Koen
%A Qu, Lizhen
%A Zhu, Xiaodan
%A Solorio, Thamar
%A Gurevych, Iryna
%A Mieskes, Margot
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F tonja-etal-2026-arr
%X We present a new dataset to support AI-assisted and human studies of the peer reviewing process, based on the ARR Open Review Platform. Unlike previous similar data collections, ours, ARR-Dv2, not only contains the reviews but also author-reviewer discussions (aka rebuttal phase) and meta-reviews. We present statistical analyses of the data with respect to the overall score and the correlations among the overall score, confidence, and soundness scores. Additionally, we extend the task of Review Score Prediction also to include rebuttal data and analyze its effect on score prediction. Finally, we introduce a new task, Meta Review Score Prediction, based on a set of up to three reviews rather than a single review. Our initial results in a zero-shot setting indicate that the rebuttal data adds valuable information to the score prediction and enables reliable predictions.
%U https://aclanthology.org/2026.aacl-long.17/
%P 333-350
Markdown (Informal)
[ARR-Dv2: New Data from ACL Rolling Review and its Potential to Improve Reviewing in the ACL Community](https://aclanthology.org/2026.aacl-long.17/) (Tonja et al., AACL-IJCNLP 2026)
ACL
- Atnafu Lambebo Tonja, Sheng Lu, Nils Dycke, Dirk Hovy, Koen Dercksen, Lizhen Qu, Xiaodan Zhu, Thamar Solorio, Iryna Gurevych, and Margot Mieskes. 2026. ARR-Dv2: New Data from ACL Rolling Review and its Potential to Improve Reviewing in the ACL Community. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 333–350, Hengqin, China. Association for Computational Linguistics.