A Conceptual Model for Born-Accessible Web Accessibility Regeneration Using Large Language Models

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.