MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Zhiyu, Zhou, Zihan, Wang, Shuo, Cong, Xin, Han, Xu, Yan, Yukun, Liu, Zhenghao, Tan, Zhixing, Liu, Pengyuan, Yu, Dong, Liu, Zhiyuan, Shi, Xiaodong, Sun, Maosong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929281903362048
author Yang, Zhiyu
Zhou, Zihan
Wang, Shuo
Cong, Xin
Han, Xu
Yan, Yukun
Liu, Zhenghao
Tan, Zhixing
Liu, Pengyuan
Yu, Dong
Liu, Zhiyuan
Shi, Xiaodong
Sun, Maosong
author_facet Yang, Zhiyu
Zhou, Zihan
Wang, Shuo
Cong, Xin
Han, Xu
Yan, Yukun
Liu, Zhenghao
Tan, Zhixing
Liu, Pengyuan
Yu, Dong
Liu, Zhiyuan
Shi, Xiaodong
Sun, Maosong
contents Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11453
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Yang, Zhiyu
Zhou, Zihan
Wang, Shuo
Cong, Xin
Han, Xu
Yan, Yukun
Liu, Zhenghao
Tan, Zhixing
Liu, Pengyuan
Yu, Dong
Liu, Zhiyuan
Shi, Xiaodong
Sun, Maosong
Computation and Language
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores.
title MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
topic Computation and Language
url https://arxiv.org/abs/2402.11453