ScreenAudit: Detecting Screen Reader Accessibility Errors in Mobile Apps Using Large Language Models
arXiv:2504.02110 · doi:10.1145/3706598.3713797
Abstract
Many mobile apps are inaccessible, thereby excluding people from their potential benefits. Existing rule-based accessibility checkers aim to mitigate these failures by identifying errors early during development but are constrained in the types of errors they can detect. We present ScreenAudit, an LLM-powered system designed to traverse mobile app screens, extract metadata and transcripts, and identify screen reader accessibility errors overlooked by existing checkers. We recruited six accessibility experts including one screen reader user to evaluate ScreenAudit's reports across 14 unique app screens. Our findings indicate that ScreenAudit achieves an average coverage of 69.2%, compared to only 31.3% with a widely-used accessibility checker. Expert feedback indicated that ScreenAudit delivered higher-quality feedback and addressed more aspects of screen reader accessibility compared to existing checkers, and that ScreenAudit would benefit app developers in real-world settings.
CHI 2025
References in corpus (5)
- Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots
- AXNav: Replaying Accessibility Tests from Natural Language
- HelpViz: Automatic Generation of Contextual Visual MobileTutorials from Text-Based Instructions
- Automatic Macro Mining from Interaction Traces at Scale
- CXSimulator: A User Behavior Simulation using LLM Embeddings for Web-Marketing Campaign Assessment