Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Cheng, Shi, Chufan, Liu, Yaxin, Shui, Bo, Wang, Junjie, Jing, Mohan, Xu, Linran, Zhu, Xinyu, Li, Siheng, Zhang, Yuxiang, Liu, Gongye, Nie, Xiaomei, Cai, Deng, Yang, Yujiu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.09961
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913711823781888
author Yang, Cheng
Shi, Chufan
Liu, Yaxin
Shui, Bo
Wang, Junjie
Jing, Mohan
Xu, Linran
Zhu, Xinyu
Li, Siheng
Zhang, Yuxiang
Liu, Gongye
Nie, Xiaomei
Cai, Deng
Yang, Yujiu
author_facet Yang, Cheng
Shi, Chufan
Liu, Yaxin
Shui, Bo
Wang, Junjie
Jing, Mohan
Xu, Linran
Zhu, Xinyu
Li, Siheng
Zhang, Yuxiang
Liu, Gongye
Nie, Xiaomei
Cai, Deng
Yang, Yujiu
contents We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 4,800 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains (e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 201 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of $3$ proprietary models and 14 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4o, InternVL2-Llama3-76B only achieved an average score across Direct Mimic and Customized Mimic tasks of 82.2 and 61.6, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09961
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
Yang, Cheng
Shi, Chufan
Liu, Yaxin
Shui, Bo
Wang, Junjie
Jing, Mohan
Xu, Linran
Zhu, Xinyu
Li, Siheng
Zhang, Yuxiang
Liu, Gongye
Nie, Xiaomei
Cai, Deng
Yang, Yujiu
Software Engineering
Computation and Language
Computer Vision and Pattern Recognition
We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 4,800 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains (e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 201 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of $3$ proprietary models and 14 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4o, InternVL2-Llama3-76B only achieved an average score across Direct Mimic and Customized Mimic tasks of 82.2 and 61.6, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.
title ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
topic Software Engineering
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.09961