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.

ChatGPT’s memory feature is designed to provide users with greater control and more helpful responses. Yet, it remains unclear how users perceive this feature in relation to privacy. To address this gap, we conducted interviews with 20 ChatGPT users from diverse backgrounds. Our findings revealed four major characteristics that distinguish ChatGPT’s memory from human memory: perceived unforgetfulness, detailedness, accuracy, and lack of emotions, highlighting the machine-like nature of AI memory. Moreover, both ChatGPT’s memory and human memory were perceived as beneficial for relationship building. Notably, most participants experienced negative expectancy violations after learning what ChatGPT remembered about them. They expressed a strong need for greater visibility, accessibility, transparency, and user control in the design of future memory features. Drawing on users’ suggestions and theoretical frameworks on privacy management, we provide design implications for developing a more transparent, responsible, and user-aligned memory experience that helps them navigate privacy-personalization trade-offs when interacting with LLM-based memories.

Chain-of-thought (CoT) is a prompting strategy that helps generative AI models break down complex tasks into simple steps, potentially leading to more diverse outputs. However, its impact on user trust and experience with generative AI tools, particularly in image generation for diversity, equity, and inclusion (DEI), retains unclear. Drawing on the HAII-TIME model, we conducted an experimental study (N = 141) comparing CoT prompt coaching to a no-strategy condition. Results showed that CoT prompt coaching increased perceived contingency and user control, both of which were associated with heightened cognitive elaboration. This, in turn, led to greater trust in the AI tool and stronger perception of trust calibration. Participants also rated the AI tool as easier to use and more helpful when guided by CoT prompt coaching. We discuss theoretical implications for conceptualizing promptability as a unique AI affordance and practical implications for designing AI tools that support human-AI collaboration in DEI-related tasks.

The popularity of automated features, such as autocorrect, reflects an interesting paradox in digital media use: while users appreciate the interactivity afforded by these media, they also seem to enjoy passively observing the system perform the interaction on their behalf. We aim to understand this paradox by using the concept of interpassivity and exploring the primary gratifications users seek in automated features. Following the research methods in U&G research, we first conducted three focus groups to generate a list of 66 gratification items, which were subjected to exploratory factor analysis in a survey study (N = 498). Results show that convenience, user control, and user profiling are three distinct gratifications of automated feature usage. Furthermore, user control is universally desired across features, and user profiling motivates the use of all automated features. We discuss the implications of these findings for U&G research and interface design of automated features.

To promote data transparency, frameworks such as CrowdWorkSheets encourage documentation of annotation practices on the interfaces of AI systems, but we do not know how they affect user experience. Will the quality of labeling affect perceived credibility of training data? Does the source of annotation matter? Will a credible dataset persuade users to trust a system even if it shows racial biases in its predictions? To find out, we conducted a user study (N = 430) with a prototype of a classification system, using a 2 (labeling quality: high vs. low) × 4 (source: others-as-source vs. self-as-source cue vs. self-as-source voluntary action, vs. self-as-source forced action) × 3 (AI performance: none vs. biased vs. unbiased) experiment. We found that high-quality labeling leads to higher perceived training data credibility, which in turn enhances users’ trust in AI, but not when the system shows bias. Practical implications for explainable and ethical AI interfaces are discussed.