计算机科学
图表
编码(集合论)
解析
程序设计语言
语言模型
代码生成
人工智能
自然语言处理
无损压缩
面子(社会学概念)
数据建模
数据操作语言
源代码
中间语言
情报检索
代表(政治)
信息抽取
自然语言生成
构造语言
自然语言
软件工程
数据模型(GIS)
作者
Zhao, Xuanle,Xianzhen Luo,Shi, Qi,Chen, Chi,Wang, Shuo,Liu, Zhiyuan,Sun, Maosong
标识
DOI:10.48550/arxiv.2501.06598
摘要
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in chart understanding tasks. However, interpreting charts with textual descriptions often leads to information loss, as it fails to fully capture the dense information embedded in charts. In contrast, parsing charts into code provides lossless representations that can effectively contain all critical details. Although existing open-source MLLMs have achieved success in chart understanding tasks, they still face two major challenges when applied to chart-to-code tasks: (1) Low executability and poor restoration of chart details in the generated code and (2) Lack of large-scale and diverse training data. To address these challenges, we propose \textbf{ChartCoder}, the first dedicated chart-to-code MLLM, which leverages Code LLMs as the language backbone to enhance the executability of the generated code. Furthermore, we introduce \textbf{Chart2Code-160k}, the first large-scale and diverse dataset for chart-to-code generation, and propose the \textbf{Snippet-of-Thought (SoT)} method, which transforms direct chart-to-code generation data into step-by-step generation. Experiments demonstrate that ChartCoder, with only 7B parameters, surpasses existing open-source MLLMs on chart-to-code benchmarks, achieving superior chart restoration and code excitability. Our code is available at https://github.com/thunlp/ChartCoder.
科研通智能强力驱动
Strongly Powered by AbleSci AI