Leveraging Large Language Models for Sustainable and Inclusive Web Accessibility

The increasing complexity of modern web applications, which are composed of dynamic and asynchronous components, poses a significant challenge for digital inclusion. Traditional automated tools typically analyze only the static HTML markup generated by frontend and backend frameworks. Recent advances in Large Language Models (LLMs) offer a novel approach to enhance the validation process by directly analyzing the source code. In this paper, we investigate the capacity of LLMs to interpret and reason dynamically generated content, providing real-time feedback on web accessibility. Our findings show that LLMs can correctly anticipate the presence of accessibility violations in the generated HTML code, going beyond the capabilities of traditional validators, also evaluating possible issues due to the asynchronous execution of the web application. However, together with legitimate issues, LLMs also produced a relevant number of hallucinated or redundant violations. This study contributes to the broader effort of employing AI with the aim of improving the inclusivity and equity of the web.