The Effect of Progressive Disclosure in the Transparency of Explainable Artificial Intelligence Systems

Recent advances in artificial intelligence (AI) systems have resulted in their ability to provide precise recommendations in response to users’ questions (prompts). However, AI models are opaque, making it challenging for users to comprehend their inner workings. While the Human-Computer Interaction (HCI) community has advocated for design principles like progressive disclosure to improve transparency, we still lack empirical evidence validating its efficacy, especially in the context of LLM-based text generation. Addressing this gap, our paper delves into a user study aimed at investigating the effect of progressive disclosure and adjusting the explanations so as to adapt to users’ mental models for improving the transparency of AI text generation systems.