# Bi-Fact: A Bidirectional Factorization-based Evaluation of Intent Extraction from UI Trajectories

arXiv: https://arxiv.org/abs/2502.13149 · HTML: https://mlsanity.com/paper/2502.13149/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [Aria-UI: Visual Grounding for GUI Instructions](https://mlsanity.com/paper/2412.16256/) (2024)
- [Automatic Macro Mining from Interaction Traces at Scale](https://mlsanity.com/paper/2310.07023/) (2023)
- [Identifying User Goals from UI Trajectories](https://mlsanity.com/paper/2406.14314/) (2024)
- [SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation](https://mlsanity.com/paper/2410.08356/) (2024)

## Built on by (most cited first, 2 of 2)

- [FC-MIR: A Mobile Screen Awareness Framework for Intent-Aware Recommendation based on Frame-Compressed Multimodal Trajectory Reasoning](https://mlsanity.com/paper/2512.19107/) (2025)
- [Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition](https://mlsanity.com/paper/2509.12423/) (2025)

## Abstract (arXiv)

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.