@inproceedings{purkayastha-etal-2026-reviewing,
title = "Reviewing the Reviewer : {LLM}-Assisted Reviewer Feedback Generation for Guideline Compliance",
author = "Purkayastha, Sukannya and
Wan, Qile and
Lauscher, Anne and
Qu, Lizhen and
Gurevych, Iryna",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1317/",
pages = "29968--30008",
ISBN = "979-8-89176-459-0",
abstract = "Peer review is central to scientific quality, yet reliance on simple heuristics, namely *lazy thinking* and non-*specific* critiques, has threatened review quality. Prior work frames *lazy thinking* detection as single-label classification and stops at detection, yet review segments often exhibit multiple co-occurring issues, and reviewers benefit more from actionable, guideline-aware feedback than from labels alone. We further show that off-the-shelf LLMs prompted for feedback frequently rewrite the entire review or address the authors rather than the reviewer, motivating an inference-time approach. We introduce an LLM-driven framework that decomposes reviews into argumentative segments, identifies issues violating ACL Rolling Review (ARR) guidelines, and generates targeted feedback using issue-specific templates refined by a novel iterative, reranking-based generation algorithm. In a controlled rewriting study, our feedback reduces guideline violations by up to 92.4{\%}. We also release LazyReviewPlus, the *first* multi-label dataset of 1,309 sentences annotated for detecting *lazy thinking* and lack of *specificity*.{\textonesuperior}\par {\textonesuperior} Code and Data: https://github.com/UKPLab/emnlp2026-reviewfeedbackagent"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purkayastha-etal-2026-reviewing">
<titleInfo>
<title>Reviewing the Reviewer : LLM-Assisted Reviewer Feedback Generation for Guideline Compliance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sukannya</namePart>
<namePart type="family">Purkayastha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qile</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Lauscher</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">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Peer review is central to scientific quality, yet reliance on simple heuristics, namely *lazy thinking* and non-*specific* critiques, has threatened review quality. Prior work frames *lazy thinking* detection as single-label classification and stops at detection, yet review segments often exhibit multiple co-occurring issues, and reviewers benefit more from actionable, guideline-aware feedback than from labels alone. We further show that off-the-shelf LLMs prompted for feedback frequently rewrite the entire review or address the authors rather than the reviewer, motivating an inference-time approach. We introduce an LLM-driven framework that decomposes reviews into argumentative segments, identifies issues violating ACL Rolling Review (ARR) guidelines, and generates targeted feedback using issue-specific templates refined by a novel iterative, reranking-based generation algorithm. In a controlled rewriting study, our feedback reduces guideline violations by up to 92.4%. We also release LazyReviewPlus, the *first* multi-label dataset of 1,309 sentences annotated for detecting *lazy thinking* and lack of *specificity*.¹\par ¹ Code and Data: https://github.com/UKPLab/emnlp2026-reviewfeedbackagent</abstract>
<identifier type="citekey">purkayastha-etal-2026-reviewing</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1317/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29968</start>
<end>30008</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reviewing the Reviewer : LLM-Assisted Reviewer Feedback Generation for Guideline Compliance
%A Purkayastha, Sukannya
%A Wan, Qile
%A Lauscher, Anne
%A Qu, Lizhen
%A Gurevych, Iryna
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F purkayastha-etal-2026-reviewing
%X Peer review is central to scientific quality, yet reliance on simple heuristics, namely *lazy thinking* and non-*specific* critiques, has threatened review quality. Prior work frames *lazy thinking* detection as single-label classification and stops at detection, yet review segments often exhibit multiple co-occurring issues, and reviewers benefit more from actionable, guideline-aware feedback than from labels alone. We further show that off-the-shelf LLMs prompted for feedback frequently rewrite the entire review or address the authors rather than the reviewer, motivating an inference-time approach. We introduce an LLM-driven framework that decomposes reviews into argumentative segments, identifies issues violating ACL Rolling Review (ARR) guidelines, and generates targeted feedback using issue-specific templates refined by a novel iterative, reranking-based generation algorithm. In a controlled rewriting study, our feedback reduces guideline violations by up to 92.4%. We also release LazyReviewPlus, the *first* multi-label dataset of 1,309 sentences annotated for detecting *lazy thinking* and lack of *specificity*.¹\par ¹ Code and Data: https://github.com/UKPLab/emnlp2026-reviewfeedbackagent
%U https://aclanthology.org/2026.emnlp-main.1317/
%P 29968-30008
Markdown (Informal)
[Reviewing the Reviewer : LLM-Assisted Reviewer Feedback Generation for Guideline Compliance](https://aclanthology.org/2026.emnlp-main.1317/) (Purkayastha et al., EMNLP 2026)
ACL