LLM-Driven Accessible Interface: A Model-Based Approach

TL;DR

This paper introduces a model-based architecture leveraging LLMs to generate personalized, multimodal, and accessible user interfaces that conform to standards and support diverse user needs, demonstrated through a healthcare use case.

Contribution

It presents a novel model-driven framework combining structured profiles, adaptation rules, and prompt templates to produce accessible UIs aligned with multiple standards and tailored to individual support needs.

Findings

Generated accessible UI components like Plain-Language text and pictograms

Conformance to WCAG 2.2, EN 301 549, ISO 24495-1, and W3C COGA

Traceability and explainability through SysML v2 models

Abstract

The integration of Large Language Models (LLMs) into interactive systems opens new opportunities for adaptive user experiences, yet it also raises challenges regarding accessibility, explainability, and normative compliance. This paper presents an implemented model-driven architecture for generating personalised, multimodal, and accessibility-aligned user interfaces. The approach combines structured user profiles, declarative adaptation rules, and validated prompt templates to refine baseline accessible UI templates that conform to WCAG 2.2 and EN 301 549, tailored to cognitive and sensory support needs. LLMs dynamically transform language complexity, modality, and visual structure, producing outputs such as Plain-Language text, pictograms, and high-contrast layouts aligned with ISO 24495-1 and W3C COGA guidance. A healthcare use case demonstrates how the system generates accessible post-consultation medication instructions tailored to a user profile comprising cognitive disability and hearing impairment. SysML v2 models provide explicit traceability between user needs, adaptation rules, and normative requirements, ensuring explainable and auditable transformations. Grounded in Human-Centered AI (HCAI), the framework incorporates co-design processes and structured feedback mechanisms to guide iterative refinement and support trustworthy generative behaviour.