MAIDR Meets AI: Exploring Multimodal LLM-Based Data Visualization Interpretation by and with Blind and Low-Vision Users

Joo Young Seo, Sanchita S. Kamath, Aziz Zeidieh, Saairam Venkatesh, Sean McCurry

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper investigates how blind and low-vision (BLV) users interact with multimodal large language models (LLMs) to interpret data visualizations. Building upon our previous work on the multimodal access and interactive data representation (MAIDR) framework, our mixed-visual-ability team co-designed maidrAI, an LLM extension providing multiple AI responses to users' visual queries. To explore generative AI-based data representation, we conducted user studies with 8 BLV participants, tasking them with interpreting box plots using our system. We examined how participants personalize LLMs through prompt engineering, their preferences for data visualization descriptions, and strategies for verifying LLM responses. Our fndings highlight three dimensions afecting BLV users' decision-making process: modal preference, LLM customization, and multimodal data representation. This research contributes to designing more accessible data visualization tools for BLV users and advances the understanding of inclusive generative AI applications.

Original languageEnglish (US)
Title of host publicationASSETS 2024 - Proceedings of the 26th International ACM SIGACCESS Conference on Computers and Accessibility
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400706776
DOIs
StatePublished - Oct 27 2024
Event26th International ACM SIGACCESS Conference on Computers and Accessibility, ASSETS 2024 - St. John's, United States
Duration: Oct 28 2024Oct 30 2024

Publication series

NameASSETS 2024 - Proceedings of the 26th International ACM SIGACCESS Conference on Computers and Accessibility

Conference

Conference26th International ACM SIGACCESS Conference on Computers and Accessibility, ASSETS 2024
Country/TerritoryUnited States
CitySt. John's
Period10/28/2410/30/24

Keywords

  • Accessibility
  • Blind
  • Data Visualization
  • Generative AI
  • Large Language Models
  • Low Vision
  • Multimodality
  • Screen Readers

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'MAIDR Meets AI: Exploring Multimodal LLM-Based Data Visualization Interpretation by and with Blind and Low-Vision Users'. Together they form a unique fingerprint.

Cite this