Fostering websites accessibility: A case study on the use of the Large Language Models ChatGPT for automatic remediation
Open accessAbstract
The use of automated accessibility testing tools remains a common practice for evaluating web accessibility. However, the results obtained from these tools may not always provide a comprehensive and complete view of a site's accessibility status. The main purpose of this study is to improve web accessibility by automatically remediating non-accessible ones using Large Language Models (LLM), particularly ChatGPT. The effectiveness of the used model in detecting and remediating accessibility issues to ensure compliance with the Web Content Accessibility Guidelines (WCAG 2.1) is also discussed. By using ChatGPT as a remediation tool, this study investigates the potential of LLM in improving web accessibility. In the case study, two websites that did not adhere to the WCAG 2.1 guidelines were selected as the primary experimental subjects for the study. These websites were assessed using the web accessibility evaluation tool, WAVE, to detect accessibility issues. The identified issues served then as the basis for remediation using ChatGPT. The effectiveness of the used advanced language model as a web accessibility remediation tool was evaluated by comparing its findings with those obtained from manual accessibility testing. The results of this comparison have significant implications for stakeholders involved in achieving WCAG compliance and contribute to the development of more accessible online platforms for individuals with disabilities.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
LLMs are trained on large-scale web code corpora that frequently violate WCAG standards, leading models to reproduce inaccessible patterns in their outputs.
“LLMs are trained on large-scale web code corpora that frequently violate WCAG standards [20, 25]-leading models to reproduce inaccessible patterns in their outputs [57].”
From A Multi-Agent Framework for Accessible Web Code Generation (2026) · cites this paper as [57]
The citation [57] is attached to the claim that LLMs reproduce inaccessible patterns in their outputs. The Results and Analysis section says ChatGPT’s performance depends on training-data quality, and §4.2 says some accessibility issues required manual remediation. Neither passage says the model reproduced inaccessible code patterns or links its outputs to non-WCAG-compliant training code; searches for those points found no supporting passage. (LLM, conf=0.73)
Experimental — accuracy not yet measuredCurrent LLMs tend to prioritize visual appearance over their semantic reality.
“Current LLMs tend to prioritize visual appearance over their semantic reality, which aligns with findings of Aljedaani et al. [10], Othman et al. [57].”
From A Multi-Agent Framework for Accessible Web Code Generation (2026) · cites this paper as [57]
Section 4.1 (Accuracy; page unavailable) reports that ChatGPT remediated 37 of 39 identified accessibility errors, including missing alternative image descriptions. Section 4.2 (Effectiveness; page unavailable) notes that some issues still required manual remediation, but neither section assesses whether LLMs prioritize visual appearance over semantic meaning. Searched for that comparison and for visually correct but semantically incorrect fixes. (LLM, conf=0.75)
Experimental — accuracy not yet measuredLLMs can generate context-aware, extended textual descriptions or summaries of data that go beyond what a human might write manually for an alt text.
“LLMs can generate context-aware, extended textual descriptions or summaries of data that go beyond what a human might write manually for an alt text [9].”
From Accessible IoT Dashboard Design with AI-Enhanced Descriptions for Visually Impaired Users (2025) · cites this paper as [9]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Baidoo-Anu, D., & Owusu Ansah, L. (2023) · doi:10.2139/ssrn.4337484 · Cited by 3,004 · see citing works
BAİDOO-ANU, D., & OWUSU ANSAH, L. (2023) · Journal of AI · doi:10.61969/jai.1337500 · Cited by 1,826 · see citing works
Improving web accessibility: a study of webmaster perceptions
Lazar, J. K., Dudley, A., & Greenidge, K.-D. (2003) · Computers in Human Behavior · doi:10.1016/j.chb.2003.10.018 · Cited by 328 · see citing works
Richards, J. T., & Hanson, V. L. (2004) · International World Wide Web Conference (WWW) · doi:10.1145/988672.988683 · Cited by 106 · see citing works
Brophy, P., & Craven, J. (2007) · Library Trends · doi:10.1353/lib.2007.0029 · Cited by 100 · see citing works
Abuaddous, H. Y., Zalisham, M., & Basir, N. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.071023 · Cited by 87 · see citing works
Understanding web accessibility and its drivers
Yesilada, Y., Brajnik, G., Vigo, M., & Harper, S. (2012) · Proceedings of the International Cross-Disciplinary Conference on Web Accessibility · doi:10.1145/2207016.2207027 · Cited by 79 · see citing works
(2009) · Worcester Research and Publications (University of Worcester) · Cited by 61 · see citing works
Website accessibility: a survey of local e-government websites and legislation in Northern Ireland
Paris, M. (2006) · Universal Access in the Information Society · doi:10.1007/s10209-003-0081-7 · Cited by 49 · see citing works
Othman, A., Mutawaa, A. A., Tamimi, A. A., & Mansouri, M. A. (2023) · Sustainability · doi:10.3390/su15043853 · Cited by 28 · see citing works
Self-citationWeb accessibility automatic evaluation tools: to what extent can they be automated?
Doush, I. A., Sultan, K., Al‐Betar, M. A., AlMeraj, Z., Alyasseri, Z. A. A., & Awadallah, M. A. (2023) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-023-00127-8 · Cited by 25 · see citing works
Mada Web Accessibility Monitor Tool
Al Jabor, A. N., Adnan, F., Park, M., & Othman, A. (2021) · 2021 8th International Conference on ICT & Accessibility (ICTA) · doi:10.1109/icta54582.2021.9809423 · Cited by 7 · see citing works
Self-citationDhouib, A., Kolski, C., & Néji, M. (2021) · Universal Access in the Information Society · doi:10.1007/s10209-021-00850-y · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Turning manual web accessibility success criteria into automatic: an LLM-based approach
López-Gil, J.-M., & Pereira, J. (2025) · Universal Access in the Information Society · doi:10.1007/s10209-024-01108-z · Cited by 50 · see citing works
“To the authors’ knowledge, [31] is the only work so far that suggests using LLMs for improving website accessibility.”
InfluentialAljedaani, W., Habib, A., Aljohani, A., Eler, M., & Feng, Y. (2024) · Proceedings of the 21st International Web for All Conference · doi:10.1145/3677846.3677854 · Cited by 42 · see citing works
On the Interaction with Large Language Models for Web Accessibility: Implications and Challenges
Delnevo, G., Andruccioli, M., & Mirri, S. (2024) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51664.2024.10454680 · Cited by 38 · see citing works
“The Web Accessibility Initiative (WAI) lists a total of 166 tools on their website 1 [15].”
Background(2024) · doi:10.1145/3613904.3642939 · Cited by 31 · see citing works
Enhancing Accessibility in Software Engineering Projects with Large Language Models (LLMs)
Aljedaani, W., Eler, M. M., & Parthasarathy, P. D. (2025) · ACM Technical Symposium on Computer Science Education (SIGCSE) · doi:10.1145/3641554.3701841 · Cited by 26 · see citing works
Enhancing Web Accessibility: Automated Detection of Issues with Generative AI
He, Z., Huq, S. F., & Malek, S. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3729371 · Cited by 26 · see citing works
“Most efforts so far have focused on fixing accessibility issues using large language models (LLMs), relying on existing tools like WAVE for the detection [Huang et al. 2024; Othman et al. 2023].”
CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
Mowar, P., Peng, Y.-H., Wu, J., Steinfeld, A., & Bigham, J. P. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713335 · Cited by 31 · see citing works
“For example, a study demonstrated that prompting ChatGPT to fix identified WCAG compliance issues in source code could automatically resolve a significant number of them [55].”
Papageorgiou, G., Sarlis, V., Μaragoudakis, M., & Tjortjis, C. (2024) · Applied Sciences · doi:10.3390/app14188259 · Cited by 33 · see citing works
Towards accessible website design through artificial intelligence: A systematic literature review
Vera-Amaro, G., & Rojano-Cáceres, J. R. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107821 · Cited by 21 · see citing works
The Promise and Pitfalls of Web Accessibility Overlays for Blind and Low Vision Users
Makati, T., Tigwell, G. W., & Shinohara, K. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675650 · Cited by 16 · see citing works
Pereira, L. S., & Duarte, C. (2025) · Universal Access in the Information Society · doi:10.1007/s10209-025-01210-w · Cited by 15 · see citing works
“Finally, Othman et al. [50] demonstrated the use of ChatGPT to generate HTML code fixes for non-compliant websites, addressing issues like non-descriptive link text and color contrast problems.”
AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code
Fathallah, N., Hernández, D., & Staab, S. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746360 · Cited by 14 · see citing works
Oliveira, A. D. A., Santos, P. S. H. D., Aljedaani, W., & Eler, M. M. (2024) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2024.4321 · Cited by 13 · see citing works
“, 2022; Haggag et al ., 2022; Othman et al ., 2023; San-doval Alcocer et al ., 2024].”
LLMs for Accessibility in Mobile Apps: Detection and Repair
Aljedaani, W., Aljohani, A., Eler, M. M., Habib, A., & Do, H. (2025) · International Web for All Conference (W4A) · doi:10.1145/3744257.3744270 · Cited by 11 · see citing works
“Unlike existing studies that focus on web accessibility [10, 40, 50, 63, 81] or iOS-based mobile applications [54], our work investigates Android accessibility, a primarily unexplored area.”
Artificial intelligence in web accessibility: A systematic mapping study
Campoverde‐Molina, M., & Luján‐Mora, S. (2025) · Computer Standards & Interfaces · doi:10.1016/j.csi.2025.104055 · Cited by 13 · see citing works
Leveraging Large Language Models for Sustainable and Inclusive Web Accessibility
Andruccioli, M., Bassi, B., Delnevo, G., & Salomoni, P. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9100247 · Cited by 11 · see citing works
Król, K. (2025) · Applied Sciences · doi:10.3390/app15052292 · Cited by 9 · see citing works
Duarte, C., da Costa, M. A. B., Pereira, L. S., & Guerreiro, J. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716329 · Cited by 8 · see citing works
Patvardhan, N., Ranade, M., Vandana, & Khatwani, R. (2024) · The International Journal of Information and Learning Technology · doi:10.1108/ijilt-04-2024-0066 · Cited by 8 · see citing works
Oliveira, A. D. A., & Eler, M. M. (2024) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3702038.3702094 · Cited by 6 · see citing works
The Tabular Accessibility Dataset: A Benchmark for LLM-Based Web Accessibility Auditing
Andruccioli, M., Bassi, B., Delnevo, G., & Salomoni, P. (2025) · Data · doi:10.3390/data10090149 · Cited by 6 · see citing works
“For instance, Othman et al. [17] investigated how ChatGPT can remediate WCAG 2.1 violations identified by the WAVE tool, showing significant improvement in compliance through automated fixes.”
InfluentialAccessible IoT Dashboard Design with AI-Enhanced Descriptions for Visually Impaired Users
Stelea, G. A., Sangeorzan, L., & Enache-David, N. (2025) · Future Internet · doi:10.3390/fi17070274 · Cited by 5 · see citing works
Yu, Y., Ryskeldiev, B., Tsutsui, A., Gillingham, M., & Wang, Y. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3746353 · Cited by 8 · see citing works
“Due to the time-intensive nature of manual remediation [2], automated approaches—such as ChatGPT-based accessibility repair [40], evaluation tools [48], and context-aware image description systems [18]—have gained traction.”
Guriță, A.-E., & Vatavu, R.-D. (2025) · International Web for All Conference (W4A) · doi:10.1145/3744257.3744266 · Cited by 5 · see citing works
“Othman et al. [38] obtained promising results in LLMs remediating specific issues, with a 94% success rate, but this rate appears to be context-dependent.”
InfluentialCan Generative AI Create Accessible Websites?
Panchanadikar, R., Bhosekar, M. S., & Dixon, E. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3759755 · Cited by 6 · see citing works
Kumar, A., Padath, T., & Wang, L. L. (2025) · Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663547.3746380 · Cited by 5 · see citing works
“For instance, LLMs like ChatGPT have been used to automatically remediate web accessibility issues, ensuring compliance with WCAG guidelines and demonstrating effectiveness in comparison to manual testing methods [37].”
An Assessment of LLM-Based Auditing and Validation for Web Accessibility
Bassi, B., Delnevo, G., Franco, M., Gaggi, O., Gatto, S., Mirri, S., & Olaiya, K. (2025) · International Conference on Information Technology for Social Good (GoodIT) · doi:10.1145/3748699.3749805 · Cited by 5 · see citing works
“The rapid diffusion and adoption of Large Language Models (LLMs) has catalyzed the development of novel solutions across numerous domains, including (but not limited to) healthcare [10, 25], content moderation [9, 14], education [24], and coding and web accessibility [1, 4, 6, 17, 19].”
SceneGenA11y: How can Runtime Generative tools improve the Accessibility of a Virtual 3D Scene?
Cao, X., Ju, K. P., Li, C., & Jain, D. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720265 · Cited by 3 · see citing works
Leedy, K., Preston, M., Feng, J. H., & Rezwana, J. (2025) · International Academic Mindtrek Conference (Mindtrek) · doi:10.1145/3757980.3757989 · Cited by 3 · see citing works
“Othman et al. demonstrated that ChatGPT could automatically fix common accessibility issues such as missing alt attributes, contrast errors, and label omissions, achieving a success rate of over 94% across various HTML test cases [23].”
Conversational AI for Accessible Website Design: Integrating LLM Assistants in Website Builders
Oswal, S. K., & Oswal, H. K. (2025) · Springer eBooks · doi:10.1007/978-3-031-84681-6_22 · Cited by 3 · see citing works
Towards a Conceptual Model for Ai-Driven Web Accessibility Remediation: A Prompt-Based Approach
Vera-Amaro, G., & Rojano-Cáceres, J. R. (2025) · International Conference in Software Engineering Research and Innovation (CONISOFT) · doi:10.1109/conisoft66928.2025.00044 · Cited by 2 · see citing works
“While automated tools like Axe detect technical issues, they offer limited insight into semantic accessibility [7].”
Vera-Amaro, G., Vera-Amaro, R., Mata-Rivera, M.-F., & Rojano-Cáceres, J. R. (2026) · Technologies · doi:10.3390/technologies14050287 · Cited by 2 · see citing works
“…barrier correction LLM-based code correction LLM-supportedremediation LLM-assisted web [20] Automatic HTML correction [20] WCAG-oriented repair [20] Score improvement after remediation [44] LLM-assisted violation correction [48] Deployment-oriented automatic remediation [48] Fine-tuned…”
InfluentialA Conceptual Model for Born-Accessible Web Accessibility Regeneration Using Large Language Models
Vera-Amaro, G., & Rojano-Cáceres, J. R. (2026) · Computers · doi:10.3390/computers15060343 · Cited by 2 · see citing works
“Studies report inconsistencies, hallucinations, limited generalization, and frequent WCAG violations in generated outputs [11–13].”
InfluentialLarge Language Models for Web Accessibility: A Systematic Literature Review
Aljedaani, W., & Mollik, R. H. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800452 · Cited by 3 · see citing works
Breaking Barriers in Mobile Accessibility: A Study of LLM-Generated Native Android Interfaces
Rabelo, D. M. F., Martins, R. D. S., Santos, I., Silva, P. H. G. D., da Gama, K. S., & Viana, W. (2025) · IEEE/ACM International Conference on Mobile Software Engineering and Systems (MOBILESoft) · doi:10.1109/mobilesoft66462.2025.00010 · Cited by 7 · see citing works
“Another study, by Othman et al. [49], used ChatGPT to identify and correct accessibility issues in two selected web-sites, one in English and the other in Arabic.”
InfluentialNavigating the Educational Landscape: Unveiling the impact of ChatGPT in Teacher-Student Dynamics
Wadhwa, S., Gujrati, R., Uygun, H., & Wadhwa, K. (2024) · SDGs Studies Review. · doi:10.37497/sdgs.v5igoals.12 · Cited by 2 · see citing works
Introduction to the Special Issue on Thriving Amidst Disruptive Technologies
Gutiérrez, J., Klein, A. Z., & Hung, P. C. K. (2024) · Distributed Ledger Technologies Research and Practice · doi:10.1145/3661804 · Cited by 2 · see citing works
A Multi-Agent Framework for Accessible Web Code Generation
Aljedaani, W., Shaik, M. A., & Aljohani, A. (2026) · Proceedings of the 23rd International Web for All Conference · doi:10.1145/3800424.3800453 · Cited by 1 · see citing works
Mendoza, M., Golondrino, G. E. C., & Puello, P. (2024) · Suma de Negocios · doi:10.14349/sumneg/2024.v15.n32.a4 · Cited by 1 · see citing works
Desafios da Inteligência Artificial Generativa na Construção de Sistemas Computacionais Acessíveis
da Silva, I. M. M., Silva, M. H. P., Teran, L. A., & Mota, M. P. (2024) · doi:10.5753/waihcws.2024.244024 · Cited by 1 · see citing works
“O estudo de [Othman et al. 2023] avalia o desempenho de LLMs na detecção de rupturas de acessibili-dade segundo a Web Content Accessibility Guidelines (WCAG) em dois sites, permitindo a detecção automática de transgressões das diretrizes de acessibilidade.”
InfluentialOliveira, A. D. A., Campos, A. E. S., Zaina, L. A. M., & Eler, M. M. (2025) · Simpósio Brasileiro de Fatores Humanos em Sistemas Computacionais (IHC) · doi:10.5753/ihc.2025.10961
“The WCAG standard is globally adopted and extensively studied in scientifc research[Serra et al. 2015, Reyes Arias et al. 2022, Othman et al. 2023, Filipe et al. 2023].”
Accessibility Evaluation of LLM-Generated Android Code in React Native
Ventura, C. D., Rabelo, D. M. F., Darin, T., & Viana, W. (2025) · Simpósio Brasileiro de Fatores Humanos em Sistemas Computacionais (IHC) · doi:10.5753/ihc.2025.10833 · Cited by 3 · see citing works
“Furthermore, previous studies [Rabelo et al. 2025, Suh et al. 2025, Delnevo et al. 2024, Aljedaani et al. 2024, Othman et al. 2023] of comparison for this research.”
Xavier, L. E. O., Rabelo, D. M. F., Martins, R. D. S., & Viana, W. (2025) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia.2025.15298 · Cited by 2 · see citing works
Caption: Generating Informative Content Labels for Image Buttons Using Next-Screen Context
Zhong, M., Mallavarapu, A., & Nie, Q. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746058.3758413
Digital Accessibility Beyond Compliance: A Post-GPT World
Rajkumar, A. J. (2025) · XRDS Crossroads The ACM Magazine for Students · doi:10.1145/3778056
“They can generate context-aware accessibility recommendations that surpass conventional testing [9, 10], yet their tendency to hallucinate risks mis-leading users and eroding trust [5, 7].”
Towards Inclusive Online Education: Evaluating Accessibility in Massive Open Online Courses
Dhouib, A., & Jemni, M. (2025) · International Conference on ICT & Accessibility (ICTA) · doi:10.1109/icta-atsn68371.2025.11398209
“The Universal Design for Learning (UDL) framework offers a proactive methodology for creating accessible MOOCs [12].”
Self-citationAssessment of Integrating Llm in Websites Localisation Service
Svintsova, E., Al-Sudani, S., & Ghanem, M. C. (2025) · Conference on Cloud and Internet of Things (CIoT) · doi:10.1109/ciot67574.2025.11410137
“Research by [7] highlights LLMs’ capacity for iterative translation refinement, reducing ‘translationese’ and improving domain-specific translation through enhanced technical terminology incorporation [10].”
Ceccarini, C., Delnevo, G., Prandi, C., & Salomoni, P. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-11978-4
Penna, G. D., Buzzi, M., & Leporini, B. (2026) · Research Square · doi:10.2139/ssrn.6643942
On the Limits for Web Accessibility Evaluation Using AI Agents
de Santana, V. F., Ferraz, R., & de Deus, J. V. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800445
An Empirical Study on Evaluating Accessible Code Generation Capabilities of LLMs
Suh, H., Tafreshipour, M., Malek, S., & Ahmed, I. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3820782 · Cited by 15 · see citing works
AugmentAble: Teaming Web Augmentation and LLMs for Instant Accessibility Improvements
Mayrhofer, S. M., Klikovits, S., & Wimmer, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29372-5_28
Empowering Web Accessibility with LLM Powered Code Improvement Tool
Garg, H., Karande, A., Ganwani, D., & Ghane, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20609-1_39
Arana, C. L., Falconi, F., & Moquillaza, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30089-8_7
I Made the Choice, Did I? Exploring the Influence of Goal-Directed AI on Human Decision-Making
Wen, R., Cao, J., Gupta, K., Hoermann, S., Billinghurst, M., Nassani, A., Baghaei, N., Allan, D. D., & Piumsomboon, T. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2719171
A Hybrid Light-AI-based Framework for Accessibility Validation
Leonardi, N., Manca, M., & Paternò, F. (2026) · International Conference on Information Technology for Social Good (GoodIT) · doi:10.1145/3794786.3830785
“Othman et al.[6]employed GPT to automatically generate corrected HTML snippets from accessibility violations detected through the WAVE, while Delnevo et al. [7] explored LLM accessibility evaluation on HTML forms, tables, and images through prompt-based reasoning on isolated code snippets.”
Evaluating Large Language Models for Web Accessibility Remediation in Real-World Websites
Aljedaani, W., Gautier, K., Parthasarathy, P. D., & Clemmer, C. (2026) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3797867.3841243
“This behavior shows that pure text prompts cannot fully connect code syntax with the visual layout of a page [20].”
- Authors
- Othman, A., Dhouib, A., & Nasser Al Jabor, A.
- Affiliations
- Mada Assistive Technology Centre (QA)
- Digital Access Services Department, Mada Qatar Assistive Technology Center, Qatar
- Venue
- Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments
- Publisher
- ACM
- Published
- 2023-07-05
- Pages
- 707-713
- OpenAlex
- W4385729888
- Cited by
- 59
- References
- 13
- Citations by year
- 2026: 14 · 2025: 30 · 2024: 15
- FWCI
- 24.74
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) (publishedVersion)
- Topics
- Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Keywords
- web accessibility, ChatGPT, large language models, automated accessibility testing, WAVE tool
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
