Many traditional pictographic Augmentative and Alternative Communication (AAC) symbol sets have been carefully designed with a focus on supporting language development. However, alongside these valuable resources, there is a growing need for symbol options that reflect wider cultural experiences and offer flexible ways to express identity, personal stories, and situations, particularly for people who have language but may have lost their voice. This paper aims to illustrate how generative artificial intelligence has the potential to produce personalized, pictographic symbols in designs that encompass both photorealistic and minimalist styles whilst being situationally specific. This type of symbol creation combines the use of text to image prompts with a series of trained symbol styles and hidden templates plus a chance to describe a specific culture. The goal was to enable users to be offered a set of improved AAC symbol choices for communication charts and other activities requiring symbolization. Initial feedback from an application usability survey indicated that Symbol Creator AI could be used without prior training. Further prompt data analysis showed that acceptable pictographic representation of users improved prompts was achieved, although additional development was required to collect more comprehensive outcome data and clarify where challenges emerged.
Text simplification remains a significant challenge, especially when texts must comply with Easy-to-Read (E2R) standards. This paper explores how normative E2R guidelines can be translated into prompt configurations for Large Language Models (LLMs) to support text simplification. We compare six prompting strategies, ranging from a baseline prompt without explicitly including the UNE guidelines to one-shot and few-shot strategies. Using Gemma 3 4B, we evaluate the generated simplifications on a mixed corpus of human-written and synthetic texts, through automatic linguistic complexity metrics, and human evaluation of guideline compliance and content preservation. Results indicate that prompting strategies that explicitly incorporate the guidelines, particularly those including examples, improve compliance with UNE-based E2R requirements compared to baseline configurations. Overall, this study provides initial evidence of the potential of LLMs as a support tool for generating E2R adapted content, and also highlights the importance of future evaluation with end users.
Disability inclusive language used in scholarly writing supports equitable participation by disabled scholars and shapes discourse by avoiding marginalization of the perspectives of disabled individuals and communities. While guidance documents exist to support disability-inclusive language, applying these recommendations consistently remains challenging for many scholars. This paper presents a prototype classifier fine-tuned on a corpus of conference abstracts that leverages a lexicon constructed from nine guidance documents. An initial classifier highlighted challenges associated with over-representation of certain disability-related terms in the original corpus. To address this, we evaluated a structured data augmentation strategy using a large language model to improve coverage of under-represented terms. The resulting classifier achieved 96.28
Neurodiverse (ND) students frequently encounter barriers to participation in hybrid higher education due to limited accommodations and inaccessible technologies. Addressing this challenge, we evaluated WebMoti, a telepresence system designed with inclusive principles to enhance classroom engagement for remote ND students. WebMoti integrates video conferencing, customizable sensory controls, multiple cameras, and a robotic “hand” to create a physical presence and support autonomy. Through a three-week longitudinal case study with three ND students and their instructors, we examined engagement, presence, and usability. Findings indicate that WebMoti improved perceived presence and enabled active participation, with customizable features and physical classroom representation central to user satisfaction. Instructors valued the system for facilitating interaction, though audio management challenges were noted. This research advances the inclusive design of information systems by demonstrating how embodied telepresence and user-driven customization can foster digital inclusion for marginalized learners in hybrid learning environments.
Generative Artificial Intelligence (GenAI) systems offer new opportunities for access to information, content creation, and decision-making, but their dominant interaction paradigm poses important barriers for people with intellectual disabilities (ID). In particular, open-ended prompts, long and poorly structured responses, and limited support for refinement, verification, and personalization can increase cognitive load and hinder effective use. This paper presents an exploratory, expert-informed co-design workshop aimed at rethinking GenAI interfaces from the perspective of cognitive accessibility for people with ID. The workshop involved ten researchers with expertise in accessibility, Human-Computer Interaction, Artificial Intelligence, and inclusive design, and was structured around five key interaction challenges identified in previous empirical work: question generation, response refinement, information verification, context management, and personalization. The workshop generated a set of preliminary design concepts that point toward more guided, structured, and adaptive interaction models, including mechanisms such as step-by-step prompting, explicit refinement controls, support for source interpretation, conversation structuring, and dynamic personalization. Rather than presenting validated interface solutions, this work offers an initial map of design opportunities for cognitively accessible GenAI and provides a foundation for future participatory design, prototyping, and evaluation with people with ID.
