arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2407.08850cs.HCcs.AI

UICrit: 借助UICritique数据集增强自动化设计评估

UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset

UC Berkeley(加州大学伯克利分校);Google DeepMind(谷歌DeepMind)

Peitong Duan, Chin-yi Chen, Gang Li, Bjoern Hartmann, Yang Li

AI总结:

针对当前基于LLM的UI评估性能不及人类的问题,研究团队构建了含3059条设计反馈的UICritique数据集,借助少样本与视觉提示技术将LLM UI评估性能提升55%,并探讨了其在奖励模型训练、多模态LLM微调等方面的应用前景。

摘要:

自动化UI评估可为设计流程提供助力,例如用于对比不同UI设计,或开展自动化启发式评估。其中,基于大语言模型(LLM)的UI评估有望适配各类UI类型与评估任务,具备广泛通用性。不过,当前基于LLM的技术表现仍未达到人类评估者的水平。我们假设,通过收集针对性的UI反馈数据集,再利用该数据集提升通用LLM的性能,可改善自动评估效果。我们推出了一个针对性数据集,包含来自7名资深设计师的、针对983个移动UI的3059条设计批评与质量评分。我们开展了深度分析以明确该数据集的特征。随后我们应用该数据集,通过多种少样本与视觉提示技术,使LLM生成的UI反馈性能提升了55%。我们还探讨了该数据集的未来应用方向,包括为生成式UI技术训练奖励模型,以及微调一款可自动化UI评估的、不依赖特定工具的多模态LLM。

英文摘要:

Automated UI evaluation can be beneficial for the design process; for example, to compare different UI designs, or conduct automated heuristic evaluation. LLM-based UI evaluation, in particular, holds the promise of generalizability to a wide variety of UI types and evaluation tasks. However, current LLM-based techniques do not yet match the performance of human evaluators. We hypothesize that automatic evaluation can be improved by collecting a targeted UI feedback dataset and then using this dataset to enhance the performance of general-purpose LLMs. We present a targeted dataset of 3,059 design critiques and quality ratings for 983 mobile UIs, collected from seven experienced designers. We carried out an in-depth analysis to characterize the dataset's features. We then applied this dataset to achieve a 55% performance gain in LLM-generated UI feedback via various few-shot and visual prompting techniques. We also discuss future applications of this dataset, including training a reward model for generative UI techniques, and fine-tuning a tool-agnostic multi-modal LLM that automates UI evaluation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑