# Human or LLM? A Comparative Study on Accessible Code Generation Capability

arXiv: https://arxiv.org/abs/2503.15885 · HTML: https://mlsanity.com/paper/2503.15885/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2025.

## Built on by (most cited first, 4 of 4)

- [Towards Scalable Web Accessibility Audit with MLLMs as Copilots](https://mlsanity.com/paper/2511.03471/) (2025)
- [Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models](https://mlsanity.com/paper/2509.00963/) (2025)
- [Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding](https://mlsanity.com/paper/2509.07676/) (2025)
- [Flow-A11y: Flow-Aware Accessibility Testing](https://mlsanity.com/paper/2607.03100/) (2026)

## Abstract (arXiv)

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.