Breaking Barriers in Mobile Accessibility: A Study of LLM-Generated Native Android Interfaces
This program is tentative and subject to change.
Rapid advancements in artificial intelligence, particularly in large language models (LLMs), have opened new opportunities for automating software development tasks, including the generation of code for mobile applications. This paper examines the potential of LLMs, such as ChatGPT, to improve the accessibility of native Android apps. It evaluates whether LLM-generated code aligns with established accessibility standards, focusing on various screen layouts and prompt designs. Two studies were conducted to assess the accessibility of the generated interfaces. The first study analyzed the generation of seven types of mobile interfaces using less restrictive prompts. In contrast, the second study required the generated code to adhere to a specific interface programming model. Upon evaluation, a total of 540 accessibility issues were identified, with interfaces generated using the Jetpack Compose framework showing better performance, although still in need of improvement. Interestingly, prompts explicitly requesting accessibility often produced more errors than standard prompts, highlighting the difficulties that LLMs face in comprehending and implementing accessibility requirements. This research emphasizes the importance of refining LLM outputs when it comes to interface descriptions, as accessibility issues may be introduced into code intended for use by developers.
This program is tentative and subject to change.
Sun 27 AprDisplayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30 | |||
11:00 30mTalk | Talk 1: To be defined Research Track | ||
11:30 15mPaper | SEESAW: An Educational App for Smart Kiosks App Track Nearchos Paspallis University of Central Lancashire, Cyprus, Nicos Kasenides UCLan Cyprus, Natalie Evans Amsterdam UMC location Vrije Universiteit | ||
11:45 15mResearch paper | LLMs in Mobile Apps: Practices, Challenges, and Opportunities Research Track Kimberly Hau University of Toronto, Safwat Hassan University of Toronto, Shurui Zhou University of Toronto | ||
12:00 15mResearch paper | AccessiblePreview: Facilitating the Implementation and Visualization of Accessibility in Mobile Applications Developed with SwiftUI Research Track Samuel Brasileiro dos Santos Neto Universidade Federal do Pernambuco, Kiev Gama Universidade Federal de Pernambuco | ||
12:15 15mResearch paper | Breaking Barriers in Mobile Accessibility: A Study of LLM-Generated Native Android Interfaces Research Track Daniel Mesquita Federal University of Ceará, Ribamar Souza Federal University of Ceará, Isaac Santos Federal University of Ceará, Paulo Henrique Federal University of Ceará, Kiev Gama Universidade Federal de Pernambuco, Windson Viana Federal University of Ceará |