Literature Reviews

Reviewed research papers, articles, and publications relevant to digital accessibility.

• Toward Independent Online Shopping of the Visually Impaired Through Voice-based Computer-Using Agent

  Subin Shin, Jeesun Oh, Suhyun Kim, Seoyeon Eom, Sangwon Lee (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  This CHI 2026 paper investigates how visually impaired users might shop online independently by interacting with a voice-based Computer-Using Agent (CUA) — an AI agent built on a Large Multimodal Model (LMM) that can perceive a screen, reason about i…

  • visual impairment
  • blindness
  • low vision
  • voice interface
  • conversational user interfaces
  • AI agents
  • large multimodal models
  • online shopping
  • e-commerce accessibility
  • human-AI interaction
  • wizard-of-oz
  • qualitative research

• "I followed what felt right, not what I was told": Autonomy, Coaching, and Recognizing Bias Through AI-Mediated Dialogue

  Atieh Taheri, Hamza El Alaoui, Patrick Carrington, Jeffrey P. Bigham (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  This CHI 2026 experimental study tests whether brief AI-mediated dialogue can shift people's recognition of ableist microaggressions, and whether the direction of AI coaching (biased, inclusive, or absent) changes the nature of that shift. The author…

  • ableism
  • microaggressions
  • bias recognition
  • AI-mediated dialogue
  • large language models
  • disability studies
  • human-AI interaction
  • intervention design
  • vignette study
  • experimental HCI
  • framing
  • nudging

• From Struggle to Success: Context-Aware Guidance for Screen Reader Users in Computer Use

  Nan Chen, Jing Lu, Zilong Wang, Luna K. Qiu, Siming Chen, Yuqing Yang (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  Chen, Lu, Wang, Qiu, Chen and Yang present AskEase, an NVDA add-on that delivers on-demand, step-by-step, screen-reader-friendly guidance for blind and low-vision computer users tackling unfamiliar desktop software. The work responds to a persistent …

  • accessibility
  • screen readers
  • AI
  • LLM
  • assistive technology
  • help-seeking
  • context engineering
  • human-AI interaction
  • blind and low vision
  • NVDA
  • RAG
  • multimodal AI

• Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People

  Jazmin Collins, Sharon Y Lin, Tianqi Liu, Andrea Stevenson Won, Shiri Azenkot (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  Collins and colleagues present the first empirical user study of an AI-powered 'sighted guide' for blind and low-vision (BLV) users in social virtual reality. Social VR platforms like VRChat (40,000 concurrent players) are largely inaccessible: they …

  • virtual reality
  • social VR
  • blind and low vision
  • AI guide
  • large language model
  • sighted guide
  • embodied agent
  • avatar
  • human-AI interaction
  • user study

• Programmers Who Use Screen Readers in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility Landscape

  Nan Chen, Luna K. Qiu, Arran Zeyu Wang, Zilong Wang, Yuqing Yang (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  This two-week, three-phase longitudinal study investigates how 16 blind and low-vision (BLV) programmers who rely on screen readers engage with advanced AI code assistants, specifically GitHub Copilot in Visual Studio Code. The study was motivated by…

  • screen readers
  • blind and low vision
  • AI code assistants
  • GitHub Copilot
  • vibe coding
  • generative AI
  • human-AI interaction
  • developer tools
  • programming accessibility

• Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors

  Michelle S. Lam, Fred Hohman, Dominik Moritz, Jeffrey P. Bigham, Kenneth Holstein, Mary Beth Kery (2025) — Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST '25)

  This paper introduces "policy maps," an approach to AI policy design for large language models inspired by physical mapmaking. The core insight is that comprehensive policy coverage over an unbounded space of LLM inputs and outputs is impossible — ju…

  • AI safety
  • AI policy
  • large language models
  • AI ethics
  • model evaluation
  • content moderation
  • data visualization
  • human-AI interaction
  • AI governance

• An Intelligent Decision Support System for Stroke Rehabilitation Assessment

  Min Hun Lee (2019) — Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2019)

  This student research abstract presents an interactive multimodal machine learning approach for automatically assessing upper-limb stroke rehabilitation exercises and supporting therapist decision-making. Physical rehabilitation is critical for peopl…

  • stroke rehabilitation
  • machine learning
  • human-AI interaction
  • decision support
  • motor disability
  • kinematic analysis
  • interactive machine learning
  • Kinect

• LaMPost: Design and Evaluation of an AI-assisted Email Writing Prototype for Adults with Dyslexia

  Steven M. Goodman, Erin Buehler, Patrick Clary, Andy Coenen, Aaron Donsbach, Tiffanie N. Horne, Michal Lahav, Robert MacDonald, Rain Breaw Michaels, Ajit Narayanan, Mahima Pushkarna, Joel Riley, Alex Santana, Lei Shi, Rachel Sweeney, Phil Weaver, Ann Yuan, Meredith Ringel Morris (2022) — Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS '22)

  This paper introduces LaMPost, a prototype email-writing interface powered by Google's LaMDA large language model, designed to support adults with dyslexia through AI-assisted writing features. The research team, which included members with lived exp…

  • dyslexia
  • large language models
  • AI writing support
  • email
  • writing challenges
  • human-AI interaction
  • neurodiversity
  • text generation
  • accessibility tools

• "Not There Yet": Feasibility and Challenges of Mobile Sound Recognition to Support Deaf and Hard-of-Hearing People

  Jeremy Zhengqi Huang, Hriday Chhabria, Dhruv Jain (2023) — Proceedings of the 25th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS)

  This paper presents the first longitudinal field study of a mobile sound recognition system used by Deaf and hard of hearing (DHH) people in their daily lives. The researchers deployed SoundWatch, a smartwatch-based app that uses a deep learning mode…

  • deaf and hard of hearing
  • sound recognition
  • wearable technology
  • smartwatch
  • assistive technology
  • machine learning
  • field study
  • human-AI interaction
  • privacy

• Understanding Human-AI Misalignment in LLM-Based Job-Seeking Support for Neurodivergent Users

  Kaely Hall, Marcus Ma, Xinyue Zhang, Vedant Das Swain, Jennifer G Kim (2025) — ASSETS 2025: 27th International ACM SIGACCESS Conference on Computers and Accessibility

  This paper examines how misalignments manifest between neurodivergent job-seekers and a GPT-4-powered career support chatbot deployed by Mentra, a neuroinclusive employment platform with over 46,000 neurodivergent users. The researchers analysed 348 …

  • neurodivergence
  • large language models
  • employment
  • AI alignment
  • autism
  • ADHD
  • chatbot
  • job-seeking
  • AI bias
  • human-AI interaction