提出双向分解法评估界面操作意图提取效果
Bi-Fact: A Bidirectional Factorization-based Evaluation of Intent Extraction from UI Trajectories
- 将意图拆解为基本事实，双向比对评估
- 与人工判断相关性优于现有方法
- 适合研究GUI意图理解的学者使用
评估从图形用户界面（GUI）中提取用户意图，需要精确且细粒度的指标。本文提出Bi-Fact，一种新方法：将意图分解为原子事实，并进行双向比较以评估精确率和召回率。实验表明，Bi-Fact与人工判断的相关性优于现有指标，建立了一个更稳健的界面驱动意图理解评估框架。
原文摘要 · Abstract (English)
Evaluating intent extraction from GUIs demands accurate, fine-grained metrics. This paper introduces Bi-Fact, a novel method that decomposes intents into atomic facts and performs bidirectional comparisons to assess precision and recall. Experiments demonstrate Bi-Fact's superior correlation with human judgments compared to existing metrics, establishing a more robust evaluation framework for UI-driven intent understanding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。