Table of Contents: :: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Caduri, Sapir, Efros, Anatoly, Kahlon, Noam, Cohen, Danielle, Halpern, Yoni, Dagan, Ido
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	https://arxiv.org/abs/2502.13149
Tags:	Add Tag No Tags, Be the first to tag this record!

Table of Contents:

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.