@inproceedings{zhou-etal-2024-llm-reliable,
title = "Is {LLM} a Reliable Reviewer? A Comprehensive Evaluation of {LLM} on Automatic Paper Reviewing Tasks",
author = "Zhou, Ruiyang and
Chen, Lu and
Yu, Kai",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.816",
pages = "9340--9351",
abstract = "The use of large language models (LLM), especially ChatGPT, to help with research has come into practice. Researchers use it for timely advice and hope to obtain in-depth feedback. However, can LLM be a qualified and reliable reviewer? Although there already exist several review-related datasets, few works have carefully and thoroughly inspected model{'}s capability as a reviewer, especially the correctness of generated reviews. In this paper, we first evaluate GPT-3.5 and GPT-4 (the current top-performing LLM) on 2 types of tasks under different settings: the score prediction task and the review generation task. In addition, we propose a dataset containing 197 review-revision multiple-choice questions (RR-MCQ) with detailed labels from the review-rebuttal forum in ICLR-2023. By asking questions from technical details to the overall presentation and quality, our RR-MCQ data provides a more complete model ability assessment. The results show that LLM is generally helpful, but great caution is needed as it always makes mistakes. Although it can give passable decisions ({\textgreater} 60{\%} accuracy) on single options, completely correct answers are still rare (about 20{\%}); models are still weak on long paper processing, zero-shot scoring, and giving critical feedback like human reviewers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2024-llm-reliable">
<titleInfo>
<title>Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiyang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of large language models (LLM), especially ChatGPT, to help with research has come into practice. Researchers use it for timely advice and hope to obtain in-depth feedback. However, can LLM be a qualified and reliable reviewer? Although there already exist several review-related datasets, few works have carefully and thoroughly inspected model’s capability as a reviewer, especially the correctness of generated reviews. In this paper, we first evaluate GPT-3.5 and GPT-4 (the current top-performing LLM) on 2 types of tasks under different settings: the score prediction task and the review generation task. In addition, we propose a dataset containing 197 review-revision multiple-choice questions (RR-MCQ) with detailed labels from the review-rebuttal forum in ICLR-2023. By asking questions from technical details to the overall presentation and quality, our RR-MCQ data provides a more complete model ability assessment. The results show that LLM is generally helpful, but great caution is needed as it always makes mistakes. Although it can give passable decisions (\textgreater 60% accuracy) on single options, completely correct answers are still rare (about 20%); models are still weak on long paper processing, zero-shot scoring, and giving critical feedback like human reviewers.</abstract>
<identifier type="citekey">zhou-etal-2024-llm-reliable</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.816</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9340</start>
<end>9351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks
%A Zhou, Ruiyang
%A Chen, Lu
%A Yu, Kai
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhou-etal-2024-llm-reliable
%X The use of large language models (LLM), especially ChatGPT, to help with research has come into practice. Researchers use it for timely advice and hope to obtain in-depth feedback. However, can LLM be a qualified and reliable reviewer? Although there already exist several review-related datasets, few works have carefully and thoroughly inspected model’s capability as a reviewer, especially the correctness of generated reviews. In this paper, we first evaluate GPT-3.5 and GPT-4 (the current top-performing LLM) on 2 types of tasks under different settings: the score prediction task and the review generation task. In addition, we propose a dataset containing 197 review-revision multiple-choice questions (RR-MCQ) with detailed labels from the review-rebuttal forum in ICLR-2023. By asking questions from technical details to the overall presentation and quality, our RR-MCQ data provides a more complete model ability assessment. The results show that LLM is generally helpful, but great caution is needed as it always makes mistakes. Although it can give passable decisions (\textgreater 60% accuracy) on single options, completely correct answers are still rare (about 20%); models are still weak on long paper processing, zero-shot scoring, and giving critical feedback like human reviewers.
%U https://aclanthology.org/2024.lrec-main.816
%P 9340-9351
Markdown (Informal)
[Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks](https://aclanthology.org/2024.lrec-main.816) (Zhou et al., LREC-COLING 2024)
ACL