@inproceedings{long-etal-2025-makes,
title = "What Makes a Good Natural Language Prompt?",
author = "Long, Do Xuan and
Dinh, Duy and
Nguyen, Ngoc-Hai and
Kawaguchi, Kenji and
Chen, Nancy F. and
Joty, Shafiq and
Kan, Min-Yen",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.292/",
doi = "10.18653/v1/2025.acl-long.292",
pages = "5835--5873",
ISBN = "979-8-89176-251-0",
abstract = "As large language models (LLMs) have progressed towards more human-like and human{--}AI communications prevalent, prompting has emerged as a decisive component. However, there is limited conceptual consensus on what exactly quantifies natural language prompts. We attempt to address this question by conducting a meta-analysis surveying 150+ prompting-related papers from leading NLP and AI conferences (2022{--}2024), and blogs. We propose a property- and human-centric framework for evaluating prompt quality, encompassing 21 properties categorized into six dimensions. We then examine how existing studies assess their impact on LLMs, revealing their imbalanced support across models and tasks, and substantial research gaps. Further, we analyze correlations among properties in high-quality natural language prompts, deriving prompting recommendations. Finally, we explore multi-property prompt enhancements in reasoning tasks, observing that single-property enhancements often have the greatest impact. Our findings establish a foundation for property-centric prompt evaluation and optimization, bridging the gaps between human{--}AI communication and opening new prompting research directions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2025-makes">
<titleInfo>
<title>What Makes a Good Natural Language Prompt?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Do</namePart>
<namePart type="given">Xuan</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc-Hai</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Kawaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>As large language models (LLMs) have progressed towards more human-like and human–AI communications prevalent, prompting has emerged as a decisive component. However, there is limited conceptual consensus on what exactly quantifies natural language prompts. We attempt to address this question by conducting a meta-analysis surveying 150+ prompting-related papers from leading NLP and AI conferences (2022–2024), and blogs. We propose a property- and human-centric framework for evaluating prompt quality, encompassing 21 properties categorized into six dimensions. We then examine how existing studies assess their impact on LLMs, revealing their imbalanced support across models and tasks, and substantial research gaps. Further, we analyze correlations among properties in high-quality natural language prompts, deriving prompting recommendations. Finally, we explore multi-property prompt enhancements in reasoning tasks, observing that single-property enhancements often have the greatest impact. Our findings establish a foundation for property-centric prompt evaluation and optimization, bridging the gaps between human–AI communication and opening new prompting research directions.</abstract>
<identifier type="citekey">long-etal-2025-makes</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.292</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.292/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>5835</start>
<end>5873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Makes a Good Natural Language Prompt?
%A Long, Do Xuan
%A Dinh, Duy
%A Nguyen, Ngoc-Hai
%A Kawaguchi, Kenji
%A Chen, Nancy F.
%A Joty, Shafiq
%A Kan, Min-Yen
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F long-etal-2025-makes
%X As large language models (LLMs) have progressed towards more human-like and human–AI communications prevalent, prompting has emerged as a decisive component. However, there is limited conceptual consensus on what exactly quantifies natural language prompts. We attempt to address this question by conducting a meta-analysis surveying 150+ prompting-related papers from leading NLP and AI conferences (2022–2024), and blogs. We propose a property- and human-centric framework for evaluating prompt quality, encompassing 21 properties categorized into six dimensions. We then examine how existing studies assess their impact on LLMs, revealing their imbalanced support across models and tasks, and substantial research gaps. Further, we analyze correlations among properties in high-quality natural language prompts, deriving prompting recommendations. Finally, we explore multi-property prompt enhancements in reasoning tasks, observing that single-property enhancements often have the greatest impact. Our findings establish a foundation for property-centric prompt evaluation and optimization, bridging the gaps between human–AI communication and opening new prompting research directions.
%R 10.18653/v1/2025.acl-long.292
%U https://aclanthology.org/2025.acl-long.292/
%U https://doi.org/10.18653/v1/2025.acl-long.292
%P 5835-5873
Markdown (Informal)
[What Makes a Good Natural Language Prompt?](https://aclanthology.org/2025.acl-long.292/) (Long et al., ACL 2025)
ACL
- Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen, Kenji Kawaguchi, Nancy F. Chen, Shafiq Joty, and Min-Yen Kan. 2025. What Makes a Good Natural Language Prompt?. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5835–5873, Vienna, Austria. Association for Computational Linguistics.