@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://preview.aclanthology.org/ingestion-acl-25/2025.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."
}