Towards Scalable Web Accessibility Audit with MLLMs as Copilots

📝 Original Info

• Title: Towards Scalable Web Accessibility Audit with MLLMs as Copilots
• ArXiv ID: 2511.03471
• Date: 2025-11-05
• Authors: 정보 없음 (원문에 저자 정보가 제공되지 않음)

📝 Abstract

Ensuring web accessibility is crucial for advancing social welfare, justice, and equality in digital spaces, yet the vast majority of website user interfaces remain non-compliant, due in part to the resource-intensive and unscalable nature of current auditing practices. While WCAG-EM offers a structured methodology for site-wise conformance evaluation, it involves great human efforts and lacks practical support for execution at scale. In this work, we present an auditing framework, AAA, which operationalizes WCAG-EM through a human-AI partnership model. AAA is anchored by two key innovations: GRASP, a graph-based multimodal sampling method that ensures representative page coverage via learned embeddings of visual, textual, and relational cues; and MaC, a multimodal large language model-based copilot that supports auditors through cross-modal reasoning and intelligent assistance in high-effort tasks. Together, these components enable scalable, end-to-end web accessibility auditing, empowering human auditors with AI-enhanced assistance for real-world impact. We further contribute four novel datasets designed for benchmarking core stages of the audit pipeline. Extensive experiments demonstrate the effectiveness of our methods, providing insights that small-scale language models can serve as capable experts when fine-tuned.

💡 Deep Analysis

📄 Full Content

Reference