arXiv cs.AI· Aman Rusia, Abhijit Bhole, Prashank Gupta, Dipanjan Dey·· 9 天前AI 评分26
Design Creativity Bench：衡量 LLM 生成 UI 的创造力
Design Creativity Bench: Measuring creativity in LLM-Generated UI
AI 导读
研究团队推出 Design Creativity Bench，从原创性、创意跨度和适配度三个维度评测 LLM 生成 UI 设计的多样性与合理性。不同模型对同一提示词的设计原创性仅 0.592，人类与模型配对为 0.764；创意跨度上模型为 0.581，人类设计达 0.902。所有模型适配度均超 90%，最佳模型达 99.2%，略高于人类的 98.0%，但默认输出明显比人类更重复。
正文 · 原文
Abstract:As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised. Our work introduces Design Creativity Bench, a benchmark that evaluates diversity and appropriateness in UI designs. It measures distinctiveness among models on the same prompt (originality), how much a model's designs change between two prompts for the same UI goal in different product domains (creative range), and the share of a brief's acceptance criteria each design meets (appropriateness). Originality is 0.592 for same-prompt design pairs from different models (95% CI [0.582, 0.602]), far below the 0.764 for same-prompt human-model pairs (95% CI [0.751, 0.778]). Creative range is 0.581 across models (95% CI [0.567, 0.597]), against 0.902 for human designs (95% CI [0.884, 0.919]). Appropriateness is above 90% for every model, and the best model reaches 99.2%, slightly above the 98.0% for human designs. Our work shows that the default output of LLMs, though generally appropriate, is substantially more repetitive than the human baseline. This calls for strong measures to address the issue.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11539 [cs.HC] |
| (or arXiv:2610.11539v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11539 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abhijit Bhole [view email]
[v1]
Thu, 8 Oct 2026 09:09:33 UTC (1,719 KB)
来源：arXiv cs.AI · arxiv.org