@inproceedings{fu-etal-2024-gptscore,
title = "{GPTS}core: Evaluate as You Desire",
author = "Fu, Jinlan and
Ng, See-Kiong and
Jiang, Zhengbao and
Liu, Pengfei",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.365",
doi = "10.18653/v1/2024.naacl-long.365",
pages = "6556--6576",
abstract = "Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently.This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., in-context learning, zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., Flan-T5-small) to 175B (e.g., GPT3).Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions.This nature helps us overcome several long-standing challenges in text evaluation{--}how to achieve customized, multi-faceted evaluation without model training. We make our code publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2024-gptscore">
<titleInfo>
<title>GPTScore: Evaluate as You Desire</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinlan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">See-Kiong</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengbao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently.This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., in-context learning, zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., Flan-T5-small) to 175B (e.g., GPT3).Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions.This nature helps us overcome several long-standing challenges in text evaluation–how to achieve customized, multi-faceted evaluation without model training. We make our code publicly available.</abstract>
<identifier type="citekey">fu-etal-2024-gptscore</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.365</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.365</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>6556</start>
<end>6576</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPTScore: Evaluate as You Desire
%A Fu, Jinlan
%A Ng, See-Kiong
%A Jiang, Zhengbao
%A Liu, Pengfei
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F fu-etal-2024-gptscore
%X Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently.This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., in-context learning, zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., Flan-T5-small) to 175B (e.g., GPT3).Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions.This nature helps us overcome several long-standing challenges in text evaluation–how to achieve customized, multi-faceted evaluation without model training. We make our code publicly available.
%R 10.18653/v1/2024.naacl-long.365
%U https://aclanthology.org/2024.naacl-long.365
%U https://doi.org/10.18653/v1/2024.naacl-long.365
%P 6556-6576
Markdown (Informal)
[GPTScore: Evaluate as You Desire](https://aclanthology.org/2024.naacl-long.365) (Fu et al., NAACL 2024)
ACL
- Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2024. GPTScore: Evaluate as You Desire. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6556–6576, Mexico City, Mexico. Association for Computational Linguistics.