arXiv：cs.AI· Lana Do, Shasta Ihorn, Charity M. Pitcher-Cooper, Sanjay Mirani, Gio Jung, Hyunjoo Shim, Zhenzhen Qin, Kien T. Nguyen, Vassilis Athitsos, Ilmi Yoon·· 20 小时前
新手的 AI 草稿编辑：草稿质量如何影响音频描述创作
How Do Novice Describers Edit AI Drafts? The Role of Draft Quality in Audio Description Authoring
AI 导读
GenAD 音频描述生成管线结合无障碍指南与视频上下文信息，将新手创作者完成音频描述的时间缩短一半以上，并显著降低认知负荷；而简单无引导提示生成的基线草稿收益有限，表明 AI 辅助存在最低质量门槛。研究发现该门槛取决于内容，视觉复杂度越高，对 AI 草稿质量的要求也越高。作者据此提出设计原则：有效的 AI 辅助应针对目标内容达到相应质量门槛，而非仅仅提供草稿。
正文
Abstract: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.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.05348 [cs.HC] |
| (or arXiv:2605.05348v2 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05348 arXiv-issued DOI via DataCite |
Submission history
From: Lana Do [view email]
[v1]
Wed, 6 May 2026 18:18:15 UTC (13,293 KB)
[v2]
Mon, 12 Oct 2026 02:05:02 UTC (12,648 KB)
来源：arXiv：cs.AI · arxiv.org