用自动反馈训练模型，让小模型也能生成31类专业图表。
Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback
- 构建含31类图表的Text2Chart31数据集，支持复杂可视化。
- 无需人工标注，用强化学习提升模型生成准确率。
- 小模型性能超大型开源模型，接近闭源顶尖水平。
大型语言模型在指令微调任务中表现优异，但在真实世界数据的图表生成上仍面临挑战。现有数据集缺乏3D、体绘制和网格图等多样图表类型；监督微调未充分利用文本、代码与图像间的复杂关联。为此，本文提出一种分层管道与新数据集Text2Chart31，包含31种基于Matplotlib的图表类型，共11.1K个描述、代码、数据表与图表对。引入基于强化学习的指令微调方法，无需人类反馈即可优化生成效果。实验表明，该方法显著提升模型性能，使小型模型在数据可视化任务中超越大型开源模型，并媲美顶尖闭源模型。代码与数据已公开于https://github.com/fatemehpesaran310/Text2Chart31。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visualizing complex, real-world data through charts and plots. Firstly, existing datasets rarely cover a full range of chart types, such as 3D, volumetric, and gridded charts. Secondly, supervised fine-tuning methods do not fully leverage the intricate relationships within rich datasets, including text, code, and figures. To address these challenges, we propose a hierarchical pipeline and a new dataset for chart generation. Our dataset, Text2Chart31, includes 31 unique plot types referring to the Matplotlib library, with 11.1K tuples of descriptions, code, data tables, and plots. Moreover, we introduce a reinforcement learning-based instruction tuning technique for chart generation tasks without requiring human feedback. Our experiments show that this approach significantly enhances the model performance, enabling smaller models to outperform larger open-source models and be comparable to state-of-the-art proprietary models in data visualization tasks. We make the code and dataset available at https://github.com/fatemehpesaran310/Text2Chart31.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。