ChartOptimiser: Task-driven Optimisation of Chart Designs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917187387654144 |
|---|---|
| author | Wang, Yao Pan, Jiarong Shi, Danqing Hu, Zhiming Oulasvirta, Antti Bulling, Andreas |
| author_facet | Wang, Yao Pan, Jiarong Shi, Danqing Hu, Zhiming Oulasvirta, Antti Bulling, Andreas |
| contents | Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs frequently introduce possibly critical design failures, such as data manipulation and confabulation. While expert users can potentially mitigate these issues through iterative prompt engineering, this process requires substantial design knowledge and significant effort, remaining a massive barrier for the general public. In this paper, we present ChartOptimiser, an automated method for generating chart designs with fidelity, efficiency, and effectiveness. Given the inter-dependencies between individual design parameters, ChartOptimiser employs Bayesian optimisation to effectively search the chart design space for a novel objective function grounded in four perceptual metrics. Our empirical evaluations in bar and pie charts demonstrate that ChartOptimiser eliminates iterative design loops, providing non-expert users with high-quality charts that outperform LLM-generated designs in chart clarity, task-solving ease, and visual aesthetics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10180 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChartOptimiser: Task-driven Optimisation of Chart Designs Wang, Yao Pan, Jiarong Shi, Danqing Hu, Zhiming Oulasvirta, Antti Bulling, Andreas Human-Computer Interaction Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs frequently introduce possibly critical design failures, such as data manipulation and confabulation. While expert users can potentially mitigate these issues through iterative prompt engineering, this process requires substantial design knowledge and significant effort, remaining a massive barrier for the general public. In this paper, we present ChartOptimiser, an automated method for generating chart designs with fidelity, efficiency, and effectiveness. Given the inter-dependencies between individual design parameters, ChartOptimiser employs Bayesian optimisation to effectively search the chart design space for a novel objective function grounded in four perceptual metrics. Our empirical evaluations in bar and pie charts demonstrate that ChartOptimiser eliminates iterative design loops, providing non-expert users with high-quality charts that outperform LLM-generated designs in chart clarity, task-solving ease, and visual aesthetics. |
| title | ChartOptimiser: Task-driven Optimisation of Chart Designs |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.10180 |