Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.12865 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912333008207872 |
|---|---|
| author | Shen, S. Lin, Z. Liu, W. Xin, C. Dai, W. Chen, S. Wen, X. Lan, X. |
| author_facet | Shen, S. Lin, Z. Liu, W. Xin, C. Dai, W. Chen, S. Wen, X. Lan, X. |
| contents | Industrial dashboards, commonly deployed by organizations such as enterprises and governments, are increasingly crucial in data communication and decision-making support across various domains. Designing an industrial dashboard prototype is particularly challenging due to its visual complexity, which can include data visualization, layout configuration, embellishments, and animations. Additionally, in real-world industrial settings, designers often encounter numerous constraints. For instance, when companies negotiate collaborations with clients and determine design plans, they typically need to demo design prototypes and iterate on them based on mock data quickly. Such a task is very common and crucial during the ideation stage, as it not only helps save developmental costs but also avoids data-related issues such as lengthy data handover periods. However, existing authoring tools of dashboards are mostly not tailored to such prototyping needs, and motivated by these gaps, we propose DashChat, an interactive system that leverages large language models (LLMs) to generate industrial dashboard design prototypes from natural language. We collaborated closely with designers from the industry and derived the requirements based on their practical experience. First, by analyzing 114 high-quality industrial dashboards, we summarized their common design patterns and inject the identified ones into LLMs as reference. Next, we built a multi-agent pipeline powered by LLMs to understand textual requirements from users and generate practical, aesthetic prototypes. Besides, functionally distinct, parallel-operating agents are created to enable efficient generation. Then, we developed a user-friendly interface that supports text-based interaction for generating and modifying prototypes. Two user studies demonstrated that our system is both effective and efficient in supporting design prototyping. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12865 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DashChat: Interactive Authoring of Industrial Dashboard Design Prototypes through Conversation with LLM-Powered Agents Shen, S. Lin, Z. Liu, W. Xin, C. Dai, W. Chen, S. Wen, X. Lan, X. Human-Computer Interaction Industrial dashboards, commonly deployed by organizations such as enterprises and governments, are increasingly crucial in data communication and decision-making support across various domains. Designing an industrial dashboard prototype is particularly challenging due to its visual complexity, which can include data visualization, layout configuration, embellishments, and animations. Additionally, in real-world industrial settings, designers often encounter numerous constraints. For instance, when companies negotiate collaborations with clients and determine design plans, they typically need to demo design prototypes and iterate on them based on mock data quickly. Such a task is very common and crucial during the ideation stage, as it not only helps save developmental costs but also avoids data-related issues such as lengthy data handover periods. However, existing authoring tools of dashboards are mostly not tailored to such prototyping needs, and motivated by these gaps, we propose DashChat, an interactive system that leverages large language models (LLMs) to generate industrial dashboard design prototypes from natural language. We collaborated closely with designers from the industry and derived the requirements based on their practical experience. First, by analyzing 114 high-quality industrial dashboards, we summarized their common design patterns and inject the identified ones into LLMs as reference. Next, we built a multi-agent pipeline powered by LLMs to understand textual requirements from users and generate practical, aesthetic prototypes. Besides, functionally distinct, parallel-operating agents are created to enable efficient generation. Then, we developed a user-friendly interface that supports text-based interaction for generating and modifying prototypes. Two user studies demonstrated that our system is both effective and efficient in supporting design prototyping. |
| title | DashChat: Interactive Authoring of Industrial Dashboard Design Prototypes through Conversation with LLM-Powered Agents |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.12865 |