Task Mode: Dynamic Filtering for Task-Specific Web Navigation using LLMs

Modern web interfaces are unnecessarily complex to use as they overwhelm users with excess text and visuals unrelated to their current goals. Such interfaces can particularly impact screen reader users (SRUs), who may need to navigate content sequentially and thus spend minutes traversing irrelevant elements compared to vision users (VUs) who visually skim in seconds. We present Task Mode, a system that dynamically filters web content based on user-specified goals using large language models to identify and prioritize relevant elements while minimizing distractions. Our approach preserves page structure while offering multiple viewing modes tailored to different access needs. Our user study with 12 participants (6 VUs, 6 SRUs) demonstrates that our approach halved task completion time for SRUs while maintaining performance for VUs, decreasing the completion time gap between groups from 2x to 1.2x. 11 of 12 participants wanted to use Task Mode in the future, reporting that Task Mode supported completing tasks with less effort and fewer distractions. This work demonstrates how designing new interactions simultaneously for visual and non-visual access can reduce rather than reinforce accessibility disparities in future technology created by researchers and practitioners.