Is Your Prompt Detailed Enough? Exploring the Effects of Prompt Coaching on Users' Perceptions, Engagement, and Trust in Text-to-Image Generative AI Tools

Cheng Chen, Sangwook Lee, Eunchae Jang, S. Shyam Sundar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Prompts are the primary medium for interacting with generative AI tools. However, users often lack sufficient prompt literacy and motivation to fully benefit from these tools. To address this, we explore whether introducing prompt coaching into a chatbot-based generative AI interface can influence users' perceptions and engagement of prompting, and further affect their trust in the system. In a user study (N = 132), we found that prompt coaching encourages users to specify more details in their prompts, even though over half initially believed their prompts were sufficient. Furthermore, the coach increased users' cognitive elaboration, which was associated with higher perceived trust calibration. However, prompt coaching did not significantly enhance UX, although users in the coaching absent condition expressed a strong need for prompt assistance for better user experience. These findings have practical implications for the design of trustworthy and responsible generative AI interfaces.

Original languageEnglish (US)
Title of host publicationTAS 2024 - Proceedings of the 2nd International Symposium on Trustworthy Autonomous Systems
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400709890
DOIs
StatePublished - Sep 16 2024
Event2nd International Symposium on Trustworthy Autonomous Systems, TAS 2024 - Austin, United States
Duration: Sep 15 2024Sep 18 2024

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Symposium on Trustworthy Autonomous Systems, TAS 2024
Country/TerritoryUnited States
CityAustin
Period9/15/249/18/24

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'Is Your Prompt Detailed Enough? Exploring the Effects of Prompt Coaching on Users' Perceptions, Engagement, and Trust in Text-to-Image Generative AI Tools'. Together they form a unique fingerprint.

Cite this