Human or LLM? A Comparative Study on Accessible Code Generation Capability
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912284060680192 |
|---|---|
| author | Suh, Hyunjae Tafreshipour, Mahan Malek, Sam Ahmed, Iftekhar |
| author_facet | Suh, Hyunjae Tafreshipour, Mahan Malek, Sam Ahmed, Iftekhar |
| contents | Web accessibility is essential for inclusive digital experiences, yet the accessibility of LLM-generated code remains underexplored. This paper presents an empirical study comparing the accessibility of web code generated by GPT-4o and Qwen2.5-Coder-32B-Instruct-AWQ against human-written code. Results show that LLMs often produce more accessible code, especially for basic features like color contrast and alternative text, but struggle with complex issues such as ARIA attributes. We also assess advanced prompting strategies (Zero-Shot, Few-Shot, Self-Criticism), finding they offer some gains but are limited. To address these gaps, we introduce FeedA11y, a feedback-driven ReAct-based approach that significantly outperforms other methods in improving accessibility. Our work highlights the promise of LLMs for accessible code generation and emphasizes the need for feedback-based techniques to address persistent challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15885 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human or LLM? A Comparative Study on Accessible Code Generation Capability Suh, Hyunjae Tafreshipour, Mahan Malek, Sam Ahmed, Iftekhar Software Engineering Web accessibility is essential for inclusive digital experiences, yet the accessibility of LLM-generated code remains underexplored. This paper presents an empirical study comparing the accessibility of web code generated by GPT-4o and Qwen2.5-Coder-32B-Instruct-AWQ against human-written code. Results show that LLMs often produce more accessible code, especially for basic features like color contrast and alternative text, but struggle with complex issues such as ARIA attributes. We also assess advanced prompting strategies (Zero-Shot, Few-Shot, Self-Criticism), finding they offer some gains but are limited. To address these gaps, we introduce FeedA11y, a feedback-driven ReAct-based approach that significantly outperforms other methods in improving accessibility. Our work highlights the promise of LLMs for accessible code generation and emphasizes the need for feedback-based techniques to address persistent challenges. |
| title | Human or LLM? A Comparative Study on Accessible Code Generation Capability |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2503.15885 |