Prompt Coaching for Inclusiveness: A Media Literacy Approach to Increase Users’ Awareness of Algorithmic Bias and Prompting Efficacy

要旨

Large language models often produce biased or stereotypical outputs. One way to reduce this possibility is to be more inclusive in our prompts, but doing so may not come naturally to most users. Therefore, we designed a tool that coaches users to write more inclusive prompts—a strategy that leverages design friction to provide a media literacy intervention. Data from a user study (N=344) show that compared to no coaching, inclusive prompt coaching directly increased users’ awareness of algorithmic bias and their perceived prompting efficacy. It also indirectly enhanced their trust in the system and perceived trust calibration through cognitive elaboration. However, inclusive prompt coaching resulted in a less satisfying user experience. These findings have implications for ethical interventions in prompting for better communicating and combating algorithmic bias. We discuss the benefits and limitations of inclusive prompt coaching, as well as ways to balance usability for long-term adoption of generative AI systems.

受賞
Honorable Mention
著者
Cheng Chen
Oregon State University, Corvallis, Oregon, United States
Mengqi Liao
University of Georgia, Athens, Georgia, United States
Aditya Anand. Phadnis
Pennsylvania State University, State College, Pennsylvania, United States
Yao Li
The Pennsylvania State University, state college, Pennsylvania, United States
Andrew High
Penn State, State College, Pennsylvania, United States
Saeed Abdullah
Pennsylvania State University, University Park, Pennsylvania, United States
S. Shyam Sundar
The Pennsylvania State University, University Park, Pennsylvania, United States

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Ethics, Inclusion & Algorithmic Impact

P1 - Room 116
7 件の発表
2026-04-16 20:15:00
2026-04-16 21:45:00