TY - GEN
T1 - Is Your Prompt Detailed Enough?
T2 - 2nd International Symposium on Trustworthy Autonomous Systems, TAS 2024
AU - Chen, Cheng
AU - Lee, Sangwook
AU - Jang, Eunchae
AU - Sundar, S. Shyam
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2024/9/16
Y1 - 2024/9/16
N2 - 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.
AB - 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.
KW - Cognitive elaboration
KW - Generative AI
KW - Perceived trust calibration
KW - Prompt coaching
KW - User Engagement
KW - User Experience
KW - User Interface
UR - https://www.scopus.com/pages/publications/85205374149
U2 - 10.1145/3686038.3686060
DO - 10.1145/3686038.3686060
M3 - Conference contribution
AN - SCOPUS:85205374149
T3 - ACM International Conference Proceeding Series
BT - TAS 2024 - Proceedings of the 2nd International Symposium on Trustworthy Autonomous Systems
PB - Association for Computing Machinery
Y2 - 15 September 2024 through 18 September 2024
ER -