The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917350374113280 |
|---|---|
| author | Bujack, Roxana Lo, Li-Ta Stam, Ethan Biswas, Ayan Rogers, David |
| author_facet | Bujack, Roxana Lo, Li-Ta Stam, Ethan Biswas, Ayan Rogers, David |
| contents | Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one-shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs. Human evaluation, though effective, is costly and impractical at scale. To alleviate this problem, we propose an automated metric that evaluates visualization quality without relying on extensive human-labeled datasets. Instead, our approach uses the original underlying data as implicit ground truth. Specifically, we introduce a method that measures visualization quality by assessing the reconstruction accuracy of the original data from the visualization itself. This reconstruction-based metric provides an autonomous and scalable proxy for thorough human evaluation, facilitating more efficient and reliable AI-driven visualization workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16873 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality Bujack, Roxana Lo, Li-Ta Stam, Ethan Biswas, Ayan Rogers, David Human-Computer Interaction Computer Vision and Pattern Recognition Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one-shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs. Human evaluation, though effective, is costly and impractical at scale. To alleviate this problem, we propose an automated metric that evaluates visualization quality without relying on extensive human-labeled datasets. Instead, our approach uses the original underlying data as implicit ground truth. Specifically, we introduce a method that measures visualization quality by assessing the reconstruction accuracy of the original data from the visualization itself. This reconstruction-based metric provides an autonomous and scalable proxy for thorough human evaluation, facilitating more efficient and reliable AI-driven visualization workflows. |
| title | The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16873 |