Web accessibility remains a persistent challenge, particularly for visually impaired users who rely on screen readers. This study investigates the potential of large language models (LLMs) to remediate accessibility issues only through structured prompt engineering without accessibility specialization. We evaluate GPT-4o and Gemini 2.0 Flash across 20 variants from two websites using different input formats (HTML, Markdown) and template-guided strategies. Outputs were assessed with automated tools, token efficiency metrics, and manual evaluations with experts and blind users. Results show an average Lighthouse score of 93.25, with WAVE errors reduced by 92.85%. Usability evaluation yielded an average success rate of 95.83% on completed tasks, with accuracy values reaching up to 0.86. GPT-4o demonstrated greater token efficiency, while Gemini produced more visually dynamic outputs. Certain violations persisted, confirming the need for human-in-the-loop validation. Overall, findings suggest that effectively guided LLMs can streamline remediation and foster more inclusive web experiences.

While accessibility research often emphasizes the experiences of blind users as consumers of online content, far less attention has been given to their role as content authors in Content Management Systems (CMS). For blind users, the accessibility of CMS platforms is fundamental to ensure efficient navigation, content creation, and overall usability. This study investigates the accessibility challenges faced by blind authors when working with WordPress as a representative CMS, identifies barriers related to navigation and content management, and offers insights to improve inclusive design. A mixed evaluation strategy was employed, combining automated testing tools with a manual assessment based on the barrier walkthrough method. Three blind participants and one sighted participant completed representative CMS tasks—such as navigation, content editing, and menu creation—using NVDA and JAWS screen readers. In addition, an expert evaluation analyzed the severity of the identified barriers. Findings indicate that block-based and drag-and-drop interfaces remain highly inaccessible for screen reader technologies, while AI-powered image descriptions help reduce dependence on sighted assistance. Results also highlight a clear mismatch between pages considered accessible by automated tools and the barriers observed in manual testing, underscoring the limitations of automated evaluations. Overall, the study stresses the need for CMS platforms to improve navigation consistency, reduce dependence on dropdown submenus, and integrate AI support to better address the needs of blind authors.

Recent research on web accessibility has explored the use of artificial intelligence (AI), particularly large language models (LLMs), to support accessibility remediation. However, the field lacks a theoretical perspective explaining how LLMs can be integrated to systematically support this process. This study proposes a theory of LLM-assisted web accessibility remediation. It is built through the integration of qualitative evidence, prior literature, accessibility standards, and empirical studies on LLM-based remediation. The resulting theory provides an explanatory framework describing how LLMs can assist web accessibility remediation through iterative cycles of analysis, transformation, and validation, and identifies key factors including prompting strategies, input representations, and validation mechanisms. This work provides a conceptual foundation for understanding and systematically studying LLM-assisted accessibility remediation, and supports both research and practice by guiding future studies and informing the design of models, methods, tools, and accessibility engineering practices.

Web accessibility remediation using large language models (LLM) has recently gained attention; however, most approaches remain tool-centric and lack formal architectural grounding. This article introduces a formally structured conceptual model for born-accessible web remediation using LLMs. The model was derived through a systematic literature review and refined under the Design Science Research Methodology. Unlike patch-based repair strategies, it treats remediation as constrained regeneration, producing accessible content from semantically reorganized inputs. The model defines five core components—input acquisition, intermediate transformation, prompt configuration, generative inference, and output evaluation—and formalizes their interactions and decision mechanisms. A controlled demonstration using multiple LLMs (GPT, Gemini) and automated tools (Lighthouse, Axe, WAVE), complemented by checklist-based structural inspection, was conducted. Results indicate that accessibility improvement depends strongly on architectural structuring of transformation and evaluation sequencing. The formalization advances LLM-driven accessibility remediation from empirical experimentation toward a reproducible, decision-governed generative paradigm, providing a structured foundation for the systematic development of accessibility-oriented architectures, frameworks, and software systems.

This paper addresses the limited attention given to blind users as content creators in Content Management Systems (CMS), a gap that remains under-explored in web accessibility research. For blind authors, effective interaction with CMS platforms requires more than technical compliance; it demands interfaces designed with semantic clarity, predictable navigation, and meaningful feedback for screen reader users. This study investigates the accessibility barriers blind users face when performing key tasks, such as page creation, menu editing, and image publishing, using CMS platforms. A two-fold evaluation was conducted using automated tools and manual usability testing with three blind and one sighted participant, complemented by expert analysis based on the Barrier Walkthrough method. Results showed that block-based interfaces were particularly challenging, often marked as accessible by automated tools but resulting in critical usability issues during manual evaluation. The use of a text-based editor, the integration of AI-generated image descriptions, and training aligned with screen reader workflows, significantly improved usability and autonomy. These findings underscore the limitations of automated assessments and highlight the importance of user-centered design practices. Enhancing CMS accessibility requires consistent navigation structures, reduced reliance on visual interaction patterns, and the integration of AI tools that support blind content authors throughout the content creation process.