Abstract
Current Generative AI (GenAI) interfaces remain largely constrained to chatbox interaction, imposing high cognitive demands on users, particularly for individuals with intellectual disabilities (ID). These challenges include difficulties in prompt formulation, response overload, and limited mechanisms to assess information reliability. To explore alternative interaction models for cognitive accessibility, we conducted a cross-disciplinary co-design challenge involving two student cohorts (Computer Science and Industrial Design) who developed interface concepts based on the same set of functional requirements (e.g., prompt scaffolding, structured output, GUI-based refinement, transparency, and personalization).
Comparative analysis of the proposals reveals convergence on foundational requirements (notably initial calibration, proactive prompting, and direct manipulation of response fragments) and complementary contributions that outline a multi-layered support system. Computer Science teams primarily focused on structural scaffolding, emphasizing predictability, navigability, and trust through mechanisms like reliability indicators, explicit sources, and context management for long conversations. In contrast, Industrial Design teams emphasized experiential scaffolding, focusing on pacing, attention guidance, multimodality, and proactive agency, including step-by-step response flows, focus modes, and assistant-like integrations.
We synthesize these findings into a dual-layer scaffolding framework that expands the design space for cognitively accessible GenAI interaction beyond chat-centric models, motivating future work on expert refinement, technical feasibility, and empirical validation with users with ID.
Blogger's Review: This paper presents a fresh perspective on cognitive-inclusive Generative AI through interdisciplinary collaboration, highlighting the synergy of structural and experiential design. This innovative approach not only broadens the design thinking for AI interactions but also offers a more user-friendly experience for individuals with intellectual disabilities, warranting further exploration and validation in real-world applications.