Scopus

VizAgent: Towards an Intelligent and Versatile Data Visualization Framework Powered by Large Language Models

Năm XB 2025 Tạp chí / Hội thảo Advances in Information and Communication Technology: Proceedings of the 3rd … Volume 1205 LNNS DOI / Link https://doi.org/10.1007/978-3-031-80943-9_10 ↗

Tác giả

V Nguyen-The ✉ ; TQ Xuan ; H Luong-Thi-Minh

Tóm tắt

This study proposed VizAgent, a novel framework designed to address the challenges in data visualization. By leveraging the capability of Large Language Model (LLM), VizAgent automates describe data, guides users’ intentions, automatically generates visualizations for specific tasks, and compares the quality of generated visualizations across different libraries. The results demonstrated that the matplotlib library outperformed other visualization libraries in terms of success rate, suggesting opportunities for further investigation and improvement, particularly in enhancing the performance of seaborn, plotly, and ggplot visualizations. The VizAgent framework presents a promising approach to intelligent data visualization, with several avenues for extending its capabilities. These include specialized handling for certain visualization libraries, empowering users to fine-tune parameters and styling, and incorporating advanced data analysis and feature engineering capabilities. VizAgent contributes to the ongoing efforts in data visualization by providing a valuable resource for researchers, practitioners, and individuals seeking data-driven decision-making.

Tài liệu tham khảo

[1] Nguyen, V.T., Jung, K., Gupta, V.: Examining data visualization pitfalls in scientific publications. Visual Computing for Industry, Biomedicine, and Art 4, 1–15 (2021)

[2] Zhu, S., Sun, G., Jiang, Q., Zha, M., Liang, R.: A survey on automatic infographics and visualization recommendations. Visual Informatics 4(3), 24–40 (2020)

[3] Wang, C., Han, J.: Dl4scivis: A state-of-the-art survey on deep learning for scientific visualization. IEEE Transactions on Visualization and Computer Graphics (2022)

[4] Yang, W., Liu, M., Wang, Z., Liu, S.: Foundation models meet visualizations: Challenges and opportunities. Computational Visual Media, 1–26 (2024)

[5] Maddigan, P., Susnjak, T.: ‘Chat2vis: Generating data visualisations via natural language using chatgpt, codex and gpt-3 large language models’. Ieee Access (2023)

[6] Dibia, V.: LIDA: a tool for automatic generation of grammar-agnostic visualizations and infographics using large language models. In: Editor (Ed.) Book LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models (2023)

[7] Wang, C., Thompson, J., Lee, B.: Data Formulator: Ai-powered concept-driven visualization authoring. IEEE Trans. Visualizat. Comp. Graph. (2023)

[8] Marvin, G., Hellen, N., Jjingo, D., Nakatumba-Nabende, J.: Prompt Engineering in Large Language Models. In: Editor (Ed.) Book Prompt Engineering in Large Language Models, Springer, pp. 387–402 (2023)

[9] Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intel. Sys. Technol. 15(3), 1–45 (2024)

[10] Khorasani, M., Abdou, M., Fernández, J.H.: Web application development with streamlit: develop and deploy secure and scalable web applications to the cloud using a pure Python framework, Springer (2022)

[11] Omelina, L., Goga, J., Pavlovicova, J., Oravec, M., Jansen, B.: A survey of iris datasets. Image Vis. Comput. 108, 104109 (2021)

Ghi chú

Imported from Google Scholar; not found in exists.md. Metadata matched via OpenAlex (score 1.00). Abstract matched via Springer page.
← Quay lại danh sách bài báo