@inproceedings{hsu-etal-2023-gpt,
title = "{GPT}-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions",
author = "Hsu, Ting-Yao and
Huang, Chieh-Yang and
Rossi, Ryan and
Kim, Sungchul and
Giles, C. and
Huang, Ting-Hao",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.363",
doi = "10.18653/v1/2023.findings-emnlp.363",
pages = "5464--5474",
abstract = "There is growing interest in systems that generate captions for scientific figures. However, assessing these systems{'} output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 arXiv figures. We then prompted LLMs like GPT-4 and GPT-3 to score (1-6) each caption based on its potential to aid reader understanding, given relevant context such as figure-mentioning paragraphs. Results show that GPT-4, used as a zero-shot evaluator, outperformed all other models and even surpassed assessments made by computer science undergraduates, achieving a Kendall correlation score of 0.401 with Ph.D. students{'} rankings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2023-gpt">
<titleInfo>
<title>GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting-Yao</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chieh-Yang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungchul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="family">Giles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Hao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is growing interest in systems that generate captions for scientific figures. However, assessing these systems’ output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 arXiv figures. We then prompted LLMs like GPT-4 and GPT-3 to score (1-6) each caption based on its potential to aid reader understanding, given relevant context such as figure-mentioning paragraphs. Results show that GPT-4, used as a zero-shot evaluator, outperformed all other models and even surpassed assessments made by computer science undergraduates, achieving a Kendall correlation score of 0.401 with Ph.D. students’ rankings.</abstract>
<identifier type="citekey">hsu-etal-2023-gpt</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.363</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.363</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5464</start>
<end>5474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions
%A Hsu, Ting-Yao
%A Huang, Chieh-Yang
%A Rossi, Ryan
%A Kim, Sungchul
%A Giles, C.
%A Huang, Ting-Hao
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F hsu-etal-2023-gpt
%X There is growing interest in systems that generate captions for scientific figures. However, assessing these systems’ output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 arXiv figures. We then prompted LLMs like GPT-4 and GPT-3 to score (1-6) each caption based on its potential to aid reader understanding, given relevant context such as figure-mentioning paragraphs. Results show that GPT-4, used as a zero-shot evaluator, outperformed all other models and even surpassed assessments made by computer science undergraduates, achieving a Kendall correlation score of 0.401 with Ph.D. students’ rankings.
%R 10.18653/v1/2023.findings-emnlp.363
%U https://aclanthology.org/2023.findings-emnlp.363
%U https://doi.org/10.18653/v1/2023.findings-emnlp.363
%P 5464-5474
Markdown (Informal)
[GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions](https://aclanthology.org/2023.findings-emnlp.363) (Hsu et al., Findings 2023)
ACL