Is Your Prompt Detailed Enough? Exploring the Effects of Prompt Coaching on Users' Perceptions, Engagement, and Trust in Text-to-Image Generative AI Tools
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.
Authors
- Eunchae Jang (ORCID: https://orcid.org/0000-0001-7547-9050)
- Sangwook Lee (ORCID: https://orcid.org/0000-0002-3052-6308)
- S. Shyam Sundar (ORCID: https://orcid.org/0000-0002-5779-8864)
- Cheng Chen (ORCID: https://orcid.org/0000-0002-9127-3893)
Institutions
- Pennsylvania State University (US)
- Elon University (US)
- University of Colorado Boulder (US)
Publication Details
- Published
- 2024-09-16
- DOI
- https://doi.org/10.1145/3686038.3686060
- Citations
- 11
- Primary Topic
- Human-Automation Interaction and Safety
- Type
- article
- Field-Weighted Citation Impact
- 7.08