Insight: Enhancing Mobile Accessibility for Blind and Visually Impaired Users with LLMs

TL;DR

This paper presents Insight, an Android accessibility service using LLMs to improve mobile accessibility for blind and visually impaired users through natural language interaction and real-time screen summarization.

Contribution

Introduction of Insight, an LLM-based accessibility tool that enhances usability and user preference over traditional gesture-based services like TalkBack.

Findings

Insight reduced mental effort and task time.

Users preferred Insight's dialogue interface.

Users expressed the need for interruption management.

Abstract

This research paper addresses the limitations of current mobile accessibility services like TalkBack, which provide manual gesture-based sequential feedback to BVI users. Motivated by the promise of large language models (LLMs), this paper introduces Insight, an Android accessibility service that provides natural language interaction and real-time summarization of the screen. The paper performs a within-subject experimental study with users to compare Insight and TalkBack on usability factors. Results show Insight reduced mental effort and task time, and was preferred because of its dialogue interface, but users felt the need for interruption management. Results show LLM-based interfaces can significantly improve mobile accessibility, and describe the potential of hybrid solutions combining gesture and dialogue modalities towards more inclusive design.