The Sky is the Limit: Understanding How Generative AI can Enhance Screen Reader Users' Experience with Productivity Applications
Open accessThe DOI matches its Crossref record; 79 of the 79 references it cites were found in a registry or an index.
Abstract
Productivity applications including word processors, spreadsheets, and presentation tools are crucial in work, education, and personal settings. Blind users typically access these tools via screen readers (SRs) and face significant accessibility and usability challenges. Recent advancements in Generative AI (GenAI) may address these challenges by enabling natural language interactions and contextual task understanding. However, there is limited understanding of SR users' needs and attitudes toward GenAI assistance in these applications. We surveyed 99 SR users to gain a holistic understanding of the challenges they face when using productivity applications, the impact of these challenges on their productivity and independence, and their initial perceptions of AI assistance. Driven by their enthusiasm, we conducted interviews with 16 SR users to explore their attitudes toward GenAI and its potential usefulness in productivity applications. Our findings highlight its need to support existing SR workflows and the importance of enabling customization and task verification.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Moreover, any new technology must support existing workflows by BLV users and allow for verification, showing that a simple translation is not a complete solution [60].”
From Accessibility-Driven Information Transformations in Mixed-Visual Ability Work Teams (2026) · cites this paper as [60]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although these tools were already available, our participants commented that organizational policies around work information often prevented their use (also mentioned in [60]).”
From Accessibility-Driven Information Transformations in Mixed-Visual Ability Work Teams (2026) · cites this paper as [60]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Braun, V., & Clarke, V. (2012) · APA handbook of research methods in psychology, Vol 2: Research designs: Quantitative, qualitative, neuropsychological, and biological. · doi:10.1037/13620-004 · Cited by 10,299
Luger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176 · cited 2×
“Prior research has shown that virtual assistants such as Siri [14], Alexa [12] and Google Assistant [49] are beneficial for blind people [1, 2, 22, 94, 98], but are limited to lightweight tasks such as playing music, determining weather [71, 73], accessing emails, and setting reminders [2].”
Generative AI in Education and Research: Opportunities, Concerns, and Solutions
Alasadi, E. A., & Baiz, C. R. (2023) · Journal of Chemical Education · doi:10.1021/acs.jchemed.3c00323 · Cited by 463 · cited 1×
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Pradhan, A., Mehta, K., & Findlater, L. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174033 · Cited by 448 · cited 2×
“Prior research has shown that virtual assistants such as Siri [14], Alexa [12] and Google Assistant [49] are beneficial for blind people [1, 2, 22, 94, 98], but are limited to lightweight tasks such as playing music, determining weather [71, 73], accessing emails, and setting reminders [2].”
Allen, J. E., Guinn, C. I., & Horvtz, E. (1999) · IEEE Intelligent Systems · doi:10.1109/5254.796083 · Cited by 442 · cited 1×
“They perceived GenAI as a supplementary helper in this mixed-initiative setting [10], where humans or computers contribute what they are best suited for at the most appropriate time.”
ChartLlama: A Multimodal LLM for Chart Understanding and GenerationPreprint
Han, Y., Zhang, C., Chen, X., Yang, X., Wang, Z., Yu, G., Fu, B., & Zhang, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.16483 · Cited by 367 · cited 1×
“…such as identifying heading levels from plain text [104, 105], transforming inaccessible table and chart data into SR-accessible formats [52, 72], and generating alt text for images [33] could be integrated into productivity tools or implemented as suggested prompts to guide authors in…”
Talk to me: Exploring user interactions with the Amazon Alexa
Lopatovska, I., Rink, K., Knight, I., Raines, K., Cosenza, K., Williams, H., Sorsche, P., Hirsch, D., Li, Q., & Martinez, A. (2019) · Journal of Librarianship and Information Science · doi:10.1177/0961000618759414 · Cited by 298 · cited 2×
“Prior research has shown that virtual assistants such as Siri [14], Alexa [12] and Google Assistant [49] are beneficial for blind people [1, 2, 22, 94, 98], but are limited to lightweight tasks such as playing music, determining weather [71, 73], accessing emails, and setting reminders [2].”
Generative AI for Software Practitioners
Ebert, C., & Louridas, P. (2023) · IEEE Software · doi:10.1109/ms.2023.3265877 · Cited by 293
Malinka, K., Peresíni, M., Firc, A., Hujnák, O., & Janus, F. (2023) · Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1 · doi:10.1145/3587102.3588827 · Cited by 287 · cited 1×
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Design Principles for Generative AI Applications
Weisz, J. D., He, J., Muller, M., Hoefer, G., Miles, R., & Geyer, W. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642466 · Cited by 232 · cited 1×
“Considering its application in different domains, Weisz et al. [118] have introduced design principles that aid de-sign practitioners, highlighting the importance of designing for generative variability, co-creation, and imperfections.”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Wortman Vaughan, J. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.8036d03b · Cited by 210
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Vaughan, J. W. (2023) · arXiv · doi:10.48550/arxiv.2306.01941 · Cited by 209 · cited 1×
“While this could engender confdence in the system, it could also potentially result in over-trust and increased reliance on AI, as highlighted by Adnin and Das [6] and Liao and Vaughan [70].”
Understanding Blind People's Experiences with Computer-Generated Captions of Social Media Images
MacLeod, H., Bennett, C. L., Morris, M. R., & Cutrell, E. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025814 · Cited by 200 · cited 1×
“• Communicating confidence levels and uncertainty : Our study, along with prior work [9, 74], highlights that explainable AI (XAI) features such as confidence ratings can assist blind users in mitigating over-trusting AI technologies.”
Abdolrahmani, A., Kuber, R., & Branham, S. M. (2018) · Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3234695.3236344 · Cited by 172 · cited 1×
“Prior research has shown that virtual assistants such as Siri [14], Alexa [12] and Google Assistant [49] are beneficial for blind people [1, 2, 22, 94, 98], but are limited to lightweight tasks such as playing music, determining weather [71, 73], accessing emails, and setting reminders [2].”
Branham, S. M., & Kane, S. K. (2015) · Proceedings of the 17th International ACM SIGACCESS Conference on Computers & Accessibility - ASSETS '15 · doi:10.1145/2700648.2809864 · Cited by 169 · cited 1×
“As a result, blind users often require more time and effort to learn and complete tasks compared to their sighted coworkers [21, 89, 106].”
"I wouldn't say offensive but...": Disability-Centered Perspectives on Large Language Models
Gadiraju, V., Kane, S., Dev, S., Taylor, A., Wang, D., Denton, R., & Brewer, R. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3593989 · Cited by 155 · cited 3×
“Our analysis aligns with previous studies that have highlighted harmful disability representations in content produced by GenAI tools [6, 9, 43, 45, 46].”
Designing Participatory AI: Creative Professionals’ Worries and Expectations about Generative AI
Inie, N., Falk, J., & Tanimoto, S. (2023) · Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544549.3585657 · Cited by 137 · cited 1×
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
The User Experience of ChatGPT: Findings from a Questionnaire Study of Early Users
Skjuve, M., Følstad, A., & Brandtzaeg, P. B. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597144 · Cited by 135 · cited 1×
“Alharbi et al. [9] reported that blind users employ various verification methods to address GenAI inaccuracies and hallucinations [30, 108], including experimentation, sighted assistance, and cross-referencing with different devices and applications.”
Das, M., Gergle, D., & Piper, A. M. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359293 · Cited by 108 · cited 4×
“The linear nature of SR output makes it difficult to distinguish between document content and collaboration markup, understand the context of edits, and track collaborator contributions [34, 36, 100].”
InfluentialHallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
Chen, Y., Fu, Q., Yuan, Y., Wen, Z., Fan, G., Liu, D., Zhang, D., Li, Z., & Xiao, Y. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614905 · Cited by 94
Investigating and Designing for Trust in AI-powered Code Generation Tools
Wang, R., Cheng, R., Ford, D., & Zimmermann, T. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658984 · Cited by 87 · cited 1×
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Identifying and Improving Disability Bias in GPT-Based Resume Screening
Glazko, K., Mohammed, Y., Kosa, B., Potluri, V., & Mankoff, J. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658933 · Cited by 85
An Autoethnographic Case Study of Generative Artificial Intelligence's Utility for Accessibility
Glazko, K. S., Yamagami, M., Desai, A., Mack, K. A., Potluri, V., Xu, X., & Mankoff, J. (2023) · The 25th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3597638.3614548 · Cited by 80 · cited 4×
“Such tools are available through web interfaces (e.g., OpenAI ChatGPT [88]), SRs (e.g., JAWS Picture Smart AI [102]), mobile and desktop applications (e.g., Be my AI [20], Microsoft Copilot [79]), and have been found to improve accessibility for blind people [6, 9, 46, 47].”
InfluentialBranham, S. M., & Mukkath Roy, A. R. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353797 · Cited by 75 · cited 2×
“Prior research has shown that virtual assistants such as Siri [14], Alexa [12] and Google Assistant [49] are beneficial for blind people [1, 2, 22, 94, 98], but are limited to lightweight tasks such as playing music, determining weather [71, 73], accessing emails, and setting reminders [2].”
"I look at it as the king of knowledge": How Blind People Use and Understand Generative AI Tools
Adnin, R., & Das, M. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675631 · Cited by 73
Abdolrahmani, A., Storer, K. M., Roy, A. R. M., Kuber, R., & Branham, S. M. (2019) · ACM Transactions on Accessible Computing · doi:10.1145/3368426 · Cited by 68
Choi, D., Kwak, D., Cho, M., & Lee, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376569 · Cited by 54 · cited 1×
“Regardless of how GenAI is integrated, our study aligns with prior work emphasizing the importance of allowing blind users extensive customization of AI interaction styles [31, 93, 96].”
ChatGPT for Visually Impaired and Blind
Kuzdeuov, A., Mukayev, O., Nurgaliyev, S., Kunbolsyn, A., & Varol, H. A. (2024) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic60209.2024.10463430 · Cited by 48 · cited 1×
“GenAI tools, such as ChatGPT [88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Investigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision People
Gonzalez Penuela, R. E., Collins, J., Bennett, C., & Azenkot, S. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642211 · Cited by 45 · cited 4×
“Prior research in this area has primarily focused on image-based visual assistance tasks [9, 33, 47].”
InfluentialUnderstanding Blind Screen-Reader Users’ Experiences of Digital Artboards
Schaadhardt, A., Hiniker, A., & Wobbrock, J. O. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445242 · Cited by 44 · cited 8×
“This accords with prior work [99].”
InfluentialVERSE: Bridging Screen Readers and Voice Assistants for Enhanced Eyes-Free Web Search
Vtyurina, A., Fourney, A., Morris, M. R., Findlater, L., & White, R. W. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353773 · Cited by 42 · cited 2×
“They found voice commands more convenient for interacting with AI [61, 115].”
Theodorou, L., Massiceti, D., Zintgraf, L., Stumpf, S., Morrison, C., Cutrell, E., Harris, M. T., & Hofmann, K. (2021) · Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3441852.3471225 · Cited by 42 · cited 1×
“Recent research has proposed ways to mitigate these biases, including evaluating models [76, 119], implementing guardrails [103], and creating more representative datasets [11, 18, 59, 113], and conducting AI audits in collaboration with blind people [3, 43, 107].”
Das, M., McHugh, T. B., Piper, A. M., & Gergle, D. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501918 · Cited by 40 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Misfitting With AI: How Blind People Verify and Contest AI Errors
Alharbi, R., Lor, P., Herskovitz, J., Schoenebeck, S., & Brewer, R. N. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675659 · Cited by 40
A11yBoard: Making Digital Artboards Accessible to Blind and Low-Vision Users
Zhang, Z., & Wobbrock, J. O. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580655 · Cited by 37 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Accessing Google Docs via Screen Reader
Buzzi, M. C., Buzzi, M., Leporini, B., Mori, G., & Penichet, V. M. R. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-14097-6_17 · Cited by 34 · cited 2×
“SR-related issues such as the lack of keyboard commands to perform actions [25] and SRs not responding [25], as well as inconsistencies among diferent types of SRs, have also been reported across various applications [34].”
Alshaigy, B., & Grande, V. (2024) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3677045.3685493 · Cited by 34 · cited 2×
“Blind users have also encountered accessibility issues when using these tools with their SRs, particularly due to unlabeled and untagged content [6, 11].”
Leporini, B., Buzzi, M., & Hersh, M. (2021) · Proceedings of the 18th International Web for All Conference · doi:10.1145/3430263.3452433 · Cited by 33 · cited 2×
“Shared screens on video conferencing platforms remain largely inaccessible to SR users [28, 29, 68, 69, 106].”
Das, M., Piper, A. M., & Gergle, D. (2022) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3480169 · Cited by 32 · cited 3×
“…non-visual interaction and reliance on auditory feedback of SRs present numerous accessibility and usability challenges for their users, such as when understanding visual information [56, 99], obtaining overview information [109, 110], finding content [84] or working collaboratively [17, 36].”
Das, M., Fiannaca, A. J., Morris, M. R., Kane, S. K., & Bennett, C. L. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642325 · Cited by 32 · cited 3×
“Prior research in this area has primarily focused on image-based visual assistance tasks [9, 33, 47].”
CollabAlly: Accessible Collaboration Awareness in Document Editing
Lee, C. Y. P., Zhang, Z., Herskovitz, J., Seo, J., & Guo, A. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517635 · Cited by 31 · cited 2×
“Several studies have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38,…”
Leporini, B., Buzzi, M., & Hersh, M. (2023) · ACM Transactions on Accessible Computing · doi:10.1145/3573012 · Cited by 28 · cited 2×
“Shared screens on video conferencing platforms remain largely inaccessible to SR users [28, 29, 68, 69, 106].”
Peng, Y.-H., Wu, J., Bigham, J., & Pavel, A. (2022) · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3526113.3545637 · Cited by 27 · cited 1×
“…studies have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38,…”
Waqar, M. M., Aslam, M., & Farhan, M. (2019) · Symmetry · doi:10.3390/sym11020238 · Cited by 26 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Conversations with Documents. An Exploration of Document-Centered Assistance
ter Hoeve, M., Sim, R., Nouri, E., Fourney, A., de Rijke, M., & White, R. W. (2020) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.2002.00747 · Cited by 26 · cited 2×
“While these tools show promise for improving the experiences of SR users [44, 61, 112], their use in productivity-related tasks remains notably underexplored.”
Conversations with Documents: An Exploration of Document-Centered Assistance
ter Hoeve, M., Sim, R., Nouri, E., Fourney, A., de Rijke, M., & White, R. W. (2020) · Proceedings of the 2020 Conference on Human Information Interaction and Retrieval · doi:10.1145/3343413.3377971 · Cited by 25 · cited 2×
“While these tools show promise for improving the experiences of SR users [44, 61, 112], their use in productivity-related tasks remains notably underexplored.”
Speaking with My Screen Reader: Using Audio Fictions to Explore Conversational Access to Interfaces
Phutane, M., Jung, C., Chen, N., & Azenkot, S. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608404 · Cited by 25 · cited 2×
“This echoes findings of Vtyurina et al. [115] and Phutane et al. [93], who also emphasize the continued importance of SRs, even when conversational assistance is available.”
Enabling Uniform Computer Interaction Experience for Blind Users through Large Language Models
Kodandaram, S. R., Uckun, U., Bi, X., Ramakrishnan, IV, & Ashok, V. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675605 · Cited by 24 · cited 5×
“While these tools show promise for improving the experiences of SR users [44, 61, 112], their use in productivity-related tasks remains notably underexplored.”
InfluentialDesigning Conversational Multimodal 3D Printed Models with People who are Blind
Reinders, S., Ananthanarayan, S., Butler, M., & Marriott, K. (2023) · Designing Interactive Systems Conference · doi:10.1145/3563657.3595989 · Cited by 22 · cited 1×
“Regardless of how GenAI is integrated, our study aligns with prior work emphasizing the importance of allowing blind users extensive customization of AI interaction styles [31, 93, 96].”
Self-citationNon-visual navigation of spreadsheets: Enhancing accessibility of Microsoft Excel™
Doush, I. A., & Pontelli, E. (2012) · Universal Access in the Information Society · doi:10.1007/s10209-012-0272-1 · Cited by 19
Lee, H.-N., Ashok, V. G., & Ramakrishnan, I. V. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3457144 · Cited by 19 · cited 1×
“Although they are widely used around the world and have become a necessity to perform numerous tasks [67], the user interfaces for most of these applications are predominantly designed for sighted user interactions and heavily depend on visual indicators [61, 65].”
Making “Google Docs” User Interface More Accessible for Blind People
Mori, G., Buzzi, M. C., Buzzi, M., Leporini, B., & Penichet, V. M. R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20810-2_4 · Cited by 18 · cited 2×
“…non-visual interaction and reliance on auditory feedback of SRs present numerous accessibility and usability challenges for their users, such as when understanding visual information [56, 99], obtaining overview information [109, 110], fnding content [84] or working collaboratively [17, 36].”
Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access
Peng, Y.-H., Chi, P., Kannan, A., Morris, M. R., & Essa, I. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580921 · Cited by 18 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Design guidelines of a tool to help blind authors independently format their word documents
Morales, L., Arteaga, S. M., & Kurniawan, S. (2013) · CHI '13 Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/2468356.2468363 · Cited by 16 · cited 1×
“Our survey confirmed that the challenges identified in previous research continue to hold for spreadsheets [57, 106], word processing [34, 82], presentation tools [99] and video conferencing platforms [68, 69].”
An Editing Process for Blind or Visually Impaired Editors
Baker, M., Nightingale, E. M., & Bills, S. (2021) · IEEE Transactions on Professional Communication · doi:10.1109/tpc.2021.3090722 · Cited by 16 · cited 1×
“…non-visual interaction and reliance on auditory feedback of SRs present numerous accessibility and usability challenges for their users, such as when understanding visual information [56, 99], obtaining overview information [109, 110], fnding content [84] or working collaboratively [17, 36].”
Zhang, Z., Kim, G. S.-H., & Wobbrock, J. O. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608418 · Cited by 16 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Measuring the Impact of AI on Information Worker ProductivityPreprint
Edelman, B. G., Ngwe, D., & Peng, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4648686 · Cited by 16 · cited 1×
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Cha, Y., Figueira, I., Ayala, J., Edwards, E. J., Garcia, J., van der Hoek, A., & Branham, S. M. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642130 · Cited by 16
Analyzing visual layout for a non-visual presentation-document interface
Ishihara, T., Takagi, H., Itoh, T., & Asakawa, C. (2006) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/1168987.1169016 · Cited by 15 · cited 1×
“Previous studies have highlighted that SR users face challenges in accessing graphical content, such as diagrams and images, primarily due to the lack of alternative descriptions [55, 106, 120] and the inability of SRs to convey spatial information [56, 58].”
Understanding the Career Mobility of Blind and Low Vision Software Professionals
Cha, Y., Jackson, V., Figueira, I., Branham, S. M., & van der Hoek, A. (2024) · Proceedings of the 2024 IEEE/ACM 17th International Conference on Cooperative and Human Aspects of Software Engineering · doi:10.1145/3641822.3641872 · Cited by 15 · cited 1×
“Shared screens on video conferencing platforms remain largely inaccessible to SR users [28, 29, 68, 69, 106].”
Using artificial-intelligence tools to make LaTeX content accessible to blind readers
Kortemeyer, G. (2023) · TUGboat · doi:10.47397/tb/44-3/tb138kortemeyer-accessibility · Cited by 14 · cited 1×
“Another use case identifed in our study, which is also found in prior work [46, 62, 95], is the conversion of inaccessible document content into SR-accessible formats.”
Evans, D. G., Diggle, T., Kurniawan, S., & Blenkhorn, P. (2003) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2003.816868 · Cited by 12 · cited 2×
“Understanding and applying document formatting is a common challenge for SR users, often requiring sighted assistance [41, 83].”
Collaborative Editing: Collaboration, Awareness and Accessibility Issues for the Blind
Buzzi, M. C., Buzzi, M., Leporini, B., Mori, G., & Penichet, V. M. R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-45550-0_58 · Cited by 12 · cited 1×
“In document collaboration, SR users face challenges with tracking changes, comments [26], and real-time editing notifcations [36].”
AccessShare: Co-designing Data Access and Sharing with Blind People
Kamikubo, R., Zeraati, F. Z., Lee, K., & Kacorri, H. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3675612 · Cited by 11 · cited 1×
“Recent research has proposed ways to mitigate these biases, including evaluating models [76, 119], implementing guardrails [103], and creating more representative datasets [11, 18, 59, 113], and conducting AI audits in collaboration with blind people [3, 43, 107].”
Accessibility for the blind: An automated audio/tactile description of pictures in digital documents
Issa, Y. B., Mojahid, M., Oriola, B., & Vigouroux, N. (2009) · International Conference on Advances in Computational Tools for Engineering Applications · doi:10.1109/actea.2009.5227855 · Cited by 10 · cited 2×
“…non-visual interaction and reliance on auditory feedback of SRs present numerous accessibility and usability challenges for their users, such as when understanding visual information [56, 99], obtaining overview information [109, 110], fnding content [84] or working collaboratively [17, 36].”
One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AIPreprint
Clarke, C., Krishnamurthy, K., Talamonti, W. J., Kang, Y., Tang, L., & Mars, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.07123 · Cited by 10 · cited 1×
“While this lack of standardization poses usability challenges for all users in adapting to multiple assistants [32], it is particularly problematic for SR users.”
Repurposing Visual Input Modalities for Blind Users: A Case Study of Word Processors
Lee, H.-N., Ashok, V., & Ramakrishnan, I. V. (2020) · 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) · doi:10.1109/smc42975.2020.9283015 · Cited by 9 · cited 1×
“Furthermore, SR users encounter issues fnding and accessing features due to the need to navigate through menus and toolbars [25, 66, 99, 106] or because of unlabelled controls [106].”
Jiang, C., Lei, W., Kuang, E., Han, T., & Fan, M. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608423 · Cited by 9 · cited 2×
“Our survey confirmed that the challenges identified in previous research continue to hold for spreadsheets [57, 106], word processing [34, 82], presentation tools [99] and video conferencing platforms [68, 69].”
“Malicious” Pictorials: How Alt Text Matters to Screen Reader Users' Experience of Image-Dense Media
Yin, A., Sogani, R., Oewel, B., Phan, K., Park, J. S. Y., Yeo, M. A., Yazzolino, L. A., Arcos, K., Abdolrahmani, A., Blank, E., et al. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3660747 · Cited by 9 · cited 1×
“Previous studies have highlighted that SR users face challenges in accessing graphical content, such as diagrams and images, primarily due to the lack of alternative descriptions [55, 106, 120] and the inability of SRs to convey spatial information [56, 58].”
Sayago, S., & Ribera, M. (2020) · International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion (DSAI) · doi:10.1145/3439231.3440603 · Cited by 8
Screen Reading Enabled by Large Language Models
Ghosh, A., Reddy, M. P., Kodandaram, S. R., Uckun, U., Ashok, V. G., Bi, X., & Ramakrishnan, I. V. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3688491 · Cited by 8
Taming User-Interface Heterogeneity with Uniform Overlays for Blind Users
Uckun, U., Tumkur Suresh, R., Ferdous, M. J., Bi, X., Ramakrishnan, I. V., & Ashok, V. (2022) · Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization · doi:10.1145/3503252.3531317 · Cited by 7 · cited 1×
“…have aimed to improve the accessibility and usability of productivity applications for blind users by introducing feature enhancements [64, 91], interface customization [37, 64, 84, 90, 100, 114], auditory feedback [64, 109, 110], and multi-modal and interactive interfaces [35, 38, 117, 121, 122].”
Visual Cues for Data Analysis Features Amplify Challenges for Blind Spreadsheet Users
Perera, M., Lee, B., Choe, E. K., & Marriott, K. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642753 · Cited by 7 · cited 1×
“In spreadsheets, cell-by-cell navigation obscures data relationships and trends [57, 92].”
Self-citationSilva, J. S. R., Freire, A. P., & Cardoso, P. C. F. (2022) · International Web for All Conference (W4A) · doi:10.1145/3493612.3520470 · Cited by 6 · cited 1×
“For example, GenAI functionalities such as identifying heading levels from plain text [104, 105], transforming inaccessible table and chart data into SR-accessible formats [52, 72], and generating alt text for images [33] could be integrated into productivity tools or implemented as suggested…”
Outwater-Wright, S. (2020) · Journal of Visual Impairment & Blindness · doi:10.1177/0145482x19900027 · Cited by 3 · cited 1×
“As a result, blind users often require more time and efort to learn and complete tasks compared to their sighted coworkers [21, 89, 106].”
Developing an Interactive Agent for Blind and Visually Impaired People
Stragier, V., Seddati, O., & Dutoit, T. (2023) · ACM International Conference on Interactive Media Experiences · doi:10.1145/3573381.3596471 · Cited by 3
Design Guidelines of Tools for Facilitating Blind People to Independently Format Their Documents
Morales, L. M., Arteaga, S. M., Cottrell, P. S., & Kurniawan, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-08596-8_98 · Cited by 2 · cited 2×
“Understanding and applying document formatting is a common challenge for SR users, often requiring sighted assistance [41, 83].”
Visually Impaired Persons Using Microsoft PowerPoint Presentations
Jung, M., & zu Bexten, E. M. (2002) · Lecture notes in computer science · doi:10.1007/3-540-45491-8_88 · Cited by 2 · cited 1×
“Previous studies have highlighted that SR users face challenges in accessing graphical content, such as diagrams and images, primarily due to the lack of alternative descriptions [55, 106, 120] and the inability of SRs to convey spatial information [56, 58].”
Shamsujjoha, M., Lu, Q., Zhao, D., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.02205 · Cited by 1
Research works printed but not linked: 13
- Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877–1901.
- Alexia Cambon, Brent Hecht, Ben Edelman, Donald Ngwe, Sonia Jaffe, Amy Heger, Mihaela Vorvoreanu, Sida Peng, Jake Hofman, Alex Farach, Margarita Bermejo-Cano, Eric Knudsen, James Bono, Hardik Sanghavi, Sofia Spatharioti, David Rothschild, Daniel G. Goldstein, Eirini Kalliamvakou, Peter Cihon, Mert Demirer, Michael Schwarz, and Jaime Teevan. 2023. Early LLM-based Tools for Enterprise Information Workers Likely Provide Meaningful Boosts to Productivity. Technical Report. Microsoft. https://www.microsoft.com/en-us/research/publication/early-llm-based-tools-for-enterprise-information-workers-likely-provide-meaningful-boosts-to-productivity/
- Iyad Abu Doush and Enrico Pontelli. 2010. Non-visual navigation of tables in spreadsheets. In Proc. of ICCHP. 108–115.
- Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT , Vol. 1. Minneapolis, Minnesota, 2.
- Hae-Na Lee. 2023. Enhancing the Usability of Computer Applications for People With Visual Impairments via UI Augmentation. Ph. D. Dissertation. State University of New York at Stony Brook.
- Weizheng Lu Jing Zhang Ju Fan Zihao Fu Yueguo Chen and Xiaoyong Du. 2024. Large language model for table processing: A survey. arXiv preprint arXiv:https://arXiv.org/abs/2402.05121 (2024). · arXiv
- Daniela Massiceti, Camilla Longden, Agnieszka Slowik, Samuel Wills, Martin Grayson, and Cecily Morrison. 2024. Explaining CLIP’s performance disparities on data from blind/low vision users. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12172–12182.
- John Gerard Schoeberlein and Yuanqiong Wang. 2014. Usability Evaluation of an Accessible Collaborative Writing Prototype for Blind Users. Journal of Usability Studies 10 1 (2014).
- Jorge Sassaki Resende Silva Paula Christina Figueira Cardoso Raphael Winckler de Bettio Daniela Cardoso Tavares Carlos Alberto Silva Willian Massami Watanabe and André Pimenta Freire. 2024. In-Page Navigation Aids for Screen-Reader Users with Automatic Topicalisation and Labelling. ACM Transactions on Accessible Computing (2024).
- A. M. Silverman, S. J. Baguhn, M.-L. Vader, E. M. Romero, and C. H. P. So. 2025. Empowering or Excluding: Expert Insights on Inclusive Artificial Intelligence for People With Disabilities. White paper. American Foundation for the Blind. http://www.afb.org/AIResearch
- Tony Stockman. 2004. The design and evaluation of auditory access to spreadsheets. In ICAD 04-Tenth Meeting of the International Conference on Auditory Display.
- Tony Stockman, Christopher Frauenberger, and Greg Hind. 2005. Interactive sonification of spreadsheets. In ICAD 05-Eleventh Meeting of the International Conference on Auditory Display.
- Boming Xia Qinghua Lu Liming Zhu and Zhenchang Xing. 2024. Towards ai safety: A taxonomy for ai system evaluation. arXiv preprint arXiv:https://arXiv.org/abs/2404.05388 (2024). · arXiv
Cited by
Chen, N., Qiu, L. K., Wang, A. Z., Wang, Z., & Yang, Y. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790726 · Cited by 17
“Similar challenges have also been observed in the context of productivity applications [67].”
InfluentialAccessibility-Driven Information Transformations in Mixed-Visual Ability Work Teams
Zhao, Y., A. Nacenta, M., A. Sukhai, M., & Somanath, S. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790872 · Cited by 4
“Although these tools were already available, our participants commented that organizational policies around work information often prevented their use (also mentioned in [60]).”
Perera, M. U. S., Ananthanarayan, S., Goncu, C., & Marriott, K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790988 · Cited by 5
“Prior research has identified these strategies in the context of visual assistance for image-based tasks (e.g., understanding objects, surroundings [4, 29], and visualizations [59]), document reading and writing [2, 66], web browsing [66], and productivity applications [56].”
InfluentialSelf-citationFrom tabbing to talking: LLM-driven conversational agents for web form interaction
Pucci, E., Piro, L., & Matera, M. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103925 · Cited by 1
How Do Disabled Visual Artists Use GenAI Tools for Business Administration Tasks?
Hayward, J., Vincenzi, B., Karpodini, C., & Theil, A. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3759708
“GenAI adoption is rapidly increasing worldwide; specifically, in the UK, 14% of the workforce use such tools and most report productivity gains [17, 18].”
Metadata
- Authors
- Perera, M., Ananthanarayan, S., Goncu, C., & Marriott, K.
- Affiliations
- Monash University (AU)
- Venue
- Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2025-04-25
- Pages
- 1-17
- OpenAlex
- W4409736088
- Cited by
- 14
- References
- 73
- Citations by year
- 2026: 13 · 2025: 1
- FWCI
- 17.00
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by-nc-sa)
- Monash University Research Portal (Monash University) (submittedVersion, cc-by-nc-sa)
- Topics
- Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Keywords
- generative AI, screen readers, blind users, productivity applications, accessibility, usability, natural language interaction, user attitudes toward AI, customization, user independence, word processing software, spreadsheet software, presentation software
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.