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

arXiv: https://arxiv.org/abs/2507.19549 · HTML: https://mlsanity.com/paper/2507.19549/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements](https://mlsanity.com/paper/2010.04295/) (2020)
- [Metacognitive Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2402.11626/) (2024)
- [Unblind Your Apps: Predicting Natural-Language Labels for Mobile GUI Components by Deep Learning](https://mlsanity.com/paper/2003.00380/) (2020)
- [Response Generation with Context-Aware Prompt Learning](https://mlsanity.com/paper/2111.02643/) (2021)
- [Enabling Uniform Computer Interaction Experience for Blind Users through Large Language Models](https://mlsanity.com/paper/2407.19537/) (2024)
- [Accessibility in Software Practice: A Practitioner's Perspective](https://mlsanity.com/paper/2103.08778/) (2021)
- [Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation](https://mlsanity.com/paper/2406.18460/) (2024)
- [ACCESS: Prompt Engineering for Automated Web Accessibility Violation Corrections](https://mlsanity.com/paper/2401.16450/) (2024)
- [DexAssist: A Voice-Enabled Dual-LLM Framework for Accessible Web Navigation](https://mlsanity.com/paper/2411.12214/) (2024)

## Built on by (most cited first, 4 of 4)

- [Large Language Models for Web Accessibility: A Systematic Literature Review](https://mlsanity.com/paper/2605.13873/) (2026)
- [Flow-A11y: Flow-Aware Accessibility Testing](https://mlsanity.com/paper/2607.03100/) (2026)
- [From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web Accessibility](https://mlsanity.com/paper/2608.24913/) (2026)
- [Agentic Web Accessibility Auditing: A Criterion-Specific Framework for Translating WCAG Requirements into Assessments](https://mlsanity.com/paper/2609.09379/) (2026)

## Abstract (arXiv)

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%.