# How Do Novice Describers Edit AI Drafts? The Role of Draft Quality in Audio Description Authoring

arXiv: https://arxiv.org/abs/2605.05348 · HTML: https://mlsanity.com/paper/2605.05348/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 19 of 19)

- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [MM-VID: Advancing Video Understanding with GPT-4V(ision)](https://mlsanity.com/paper/2310.19773/) (2023)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding](https://mlsanity.com/paper/2412.03735/) (2024)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models](https://mlsanity.com/paper/2402.11723/) (2024)
- [AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description](https://mlsanity.com/paper/2407.15850/) (2024)
- [Rescribe: Authoring and Automatically Editing Audio Descriptions](https://mlsanity.com/paper/2010.03667/) (2020)
- [AVscript: Accessible Video Editing with Audio-Visual Scripts](https://mlsanity.com/paper/2302.14117/) (2023)
- [The Role of Inclusion, Control, and Ownership in Workplace AI-Mediated Communication](https://mlsanity.com/paper/2309.11599/) (2023)
- [LLM-AD: Large Language Model based Audio Description System](https://mlsanity.com/paper/2405.00983/) (2024)
- [Making Short-Form Videos Accessible with Hierarchical Video Summaries](https://mlsanity.com/paper/2402.10382/) (2024)
- [VideoA11y: Method and Dataset for Accessible Video Description](https://mlsanity.com/paper/2502.20480/) (2025)
- [CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding](https://mlsanity.com/paper/2208.11144/) (2022)
- [Describe Now: User-Driven Audio Description for Blind and Low Vision Individuals](https://mlsanity.com/paper/2411.11835/) (2024)
- [ADCanvas: Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators](https://mlsanity.com/paper/2602.07266/) (2026)

## Abstract (arXiv)

Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing process. We investigate this through GenAD, an AD generation pipeline that incorporates accessibility guidelines and contextual video information, and RefineAD, an editing interface for human revisions. Human-AI contributions are measured across text, timing, and delivery. In a within-subjects study, we compared authoring from scratch against editing AI drafts of varying quality. GenAD drafts cut completion time by more than half and significantly reduced cognitive load. In contrast, baseline drafts generated from simple, unguided prompts offered only modest benefits, pointing to a minimum quality threshold for effectiveness. Qualitative findings suggest this threshold is content-dependent; as visual complexity increases, so does the quality needed from AI drafts. We propose this as a design principle: effective AI assistance should clear a quality threshold suited to the target content, rather than simply be present.