Reproduce “InterA11y: Interactive Web Accessibility Error Detection with LLM Agents” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mingyuan Zhong, Mengqi Shi, Davin Win Kyi, Ajit Mallavarapu, Xia Chen, James Fogarty, Jacob O. Wobbrock
InterA11y uses checklist-guided LLMs and browser tools to audit 10 selected WCAG criteria. On 197 expert-annotated elements from offline replications of 54 webpages, it achieved mean recall of 79.0%, versus 44.4% for the highest-recall evaluated LLM-checker baseline, and mean precision of 93.1%. These results support element-level auditing, not whole-site conformance or replacement of expert review.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.