Literature Reviews

Reviewed research papers, articles, and publications relevant to digital accessibility.

• Does ChatGPT Generate Accessible Code? Investigating Accessibility Challenges in LLM-Generated Source Code

  Wajdi Aljedaani, Abdulrahman Habib, Ahmed Aljohani, Marcelo Eler, Yunhe Feng (2024) — Proceedings of the 21st International Web for All Conference (W4A)

  This paper presents the first empirical evaluation of the accessibility of web code generated by ChatGPT (GPT-3.5), examining both how accessible the generated code is and how well the model can fix accessibility violations. The study involved 88 web…

  • web accessibility
  • large language models
  • ChatGPT
  • automated testing
  • WCAG
  • code generation
  • AI accessibility

• Accessibility in AI-Assisted Web Development

  Peya Mowar (2024) — Proceedings of the 21st International Web for All Conference (W4A)

  This extended abstract from a CMU doctoral student examines whether AI code generation tools—specifically GitHub Copilot—help or hinder web accessibility when used by developers. The research is motivated by a persistent problem: despite decades of a…

  • AI code generation
  • web accessibility
  • developer practices
  • GitHub Copilot
  • automated testing
  • WCAG compliance

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

  Nadeen Fathallah, Daniel Hernández, Steffen Staab (2025) — ASSETS 2025: 27th International ACM SIGACCESS Conference on Computers and Accessibility

  This paper introduces AccessGuru, a novel method that combines traditional automated accessibility testing tools with large language models (LLMs) to both detect and correct web accessibility violations in HTML code. The work addresses a persistent g…

  • automated testing
  • web accessibility
  • large language models
  • HTML remediation
  • prompt engineering
  • WCAG
  • accessibility violations
  • machine learning

• Benchmarking PDF Accessibility Evaluation: A Dataset and Framework for Assessing Automated and LLM-Based Approaches for Accessibility Testing

  Anukriti Kumar, Tanushree Padath, Lucy Lu Wang (2025) — ASSETS 2025: 27th International ACM SIGACCESS Conference on Computers and Accessibility

  This paper addresses a critical gap in PDF accessibility evaluation by introducing the first expert-validated benchmark dataset and standardized evaluation framework for assessing how well different tools and approaches can evaluate PDF accessibility…

  • PDF accessibility
  • automated testing
  • large language models
  • WCAG
  • PDF/UA
  • benchmark dataset
  • document accessibility
  • alternative text
  • reading order
  • semantic tagging
  • accessibility evaluation

• Drop-Down Menu Widget Identification Using HTML Structure Changes Classification

  Humberto Lidio Antonelli, Rodrigo Augusto Igawa, Renata Pontin De Mattos Fortes, Eduardo Henrique Rizo, Willian Massami Watanabe (2018) — ACM Transactions on Accessible Computing (TACCESS)

  This paper addresses a critical gap in web accessibility: the widespread failure of interactive widgets in rich internet applications (RIAs) to implement WAI-ARIA markup, rendering them inaccessible to screen reader users and other assistive technolo…

  • ARIA
  • web accessibility
  • machine learning
  • widgets
  • automated testing
  • rich internet applications
  • DOM

• Uncovering the New Accessibility Crisis in Scholarly PDFs: Publishing Model and Platform Changes Contribute to Declining Scholarly Document Accessibility in the Last Decade

  Anukriti Kumar, Lucy Lu Wang (2024) — ASSETS '24: Proceedings of the 26th International ACM SIGACCESS Conference on Computers and Accessibility

  This paper presents a large-scale analysis of 20,000 scholarly PDFs published between 2014 and 2023 to characterise the scope and trajectory of document accessibility in academic publishing. Most scholarly works are distributed as PDFs, a format that…

  • PDF accessibility
  • scholarly publishing
  • document accessibility
  • screen readers
  • tagged PDF
  • alt text
  • open access
  • automated testing
  • large-scale analysis

• The WebAIM Million: An Annual Accessibility Analysis of the Top 1,000,000 Home Pages

  WebAIM (2024) — WebAIM

  Annual large-scale automated accessibility evaluation of the top one million website home pages. The study consistently reveals widespread accessibility failures, with the majority of pages containing detectable WCAG conformance errors.

  • automated testing
  • web accessibility
  • large-scale analysis