AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code

TL;DR

AccessGuru is a novel approach that leverages Large Language Models and a structured taxonomy to automatically detect and correct various types of Web accessibility violations in HTML code, promoting inclusiveness.

Contribution

The paper introduces a new taxonomy for accessibility violations and a method combining LLMs with testing tools to automatically fix violations, outperforming prior approaches.

Findings

AccessGuru reduces accessibility violations by up to 84%.

It outperforms previous methods with at most 50% improvement.

The benchmark evaluates syntactic, semantic, and layout compliance.

Abstract

The vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated expertise and additional manual efforts from Web page providers. To lower their efforts and promote inclusiveness, we aim to automatically detect and correct Web accessibility violations in HTML code. While previous work has made progress in detecting certain types of accessibility violations, the problem of automatically detecting and correcting accessibility violations remains an open challenge that we address. We introduce a novel taxonomy classifying Web accessibility violations into three key categories - Syntactic, Semantic, and Layout. This taxonomy provides a structured foundation for developing our detection and correction method and redefining evaluation metrics. We propose a novel method, AccessGuru, which combines existing accessibility testing tools and Large Language Models (LLMs) to detect violations and applies taxonomy-driven prompting strategies to correct all three categories. To evaluate these capabilities, we develop a benchmark of real-world Web accessibility violations. Our benchmark quantifies syntactic and layout compliance and judges semantic accuracy through comparative analysis with human expert corrections. Evaluation against our benchmark shows that AccessGuru achieves up to 84% average violation score decrease, significantly outperforming prior methods that achieve at most 50%.