# Towards Scalable Web Accessibility Audit with MLLMs as Copilots

arXiv: https://arxiv.org/abs/2511.03471 · HTML: https://mlsanity.com/paper/2511.03471/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs](https://mlsanity.com/paper/2407.16837/) (2024)
- [Compact Graph Structure Learning via Mutual Information Compression](https://mlsanity.com/paper/2201.05540/) (2022)
- [Homophily-enhanced Structure Learning for Graph Clustering](https://mlsanity.com/paper/2308.05309/) (2023)
- [Human or LLM? A Comparative Study on Accessible Code Generation Capability](https://mlsanity.com/paper/2503.15885/) (2025)
- [Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspective](https://mlsanity.com/paper/2412.09805/) (2024)

## Built on by (most cited first, 2 of 2)

- [Towards Scalable Lightweight GUI Agents via Multi-role Orchestration](https://mlsanity.com/paper/2604.13488/) (2026)
- [Agentic Web Accessibility Auditing: A Criterion-Specific Framework for Translating WCAG Requirements into Assessments](https://mlsanity.com/paper/2609.09379/) (2026)

## Abstract (arXiv)

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.