用自动反馈提升大模型生成图表质量，无需人工标注。
$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation
- 自动生成反馈机制ChartAF，不依赖人工标注。
- 94%用户偏好新数据集查询，93%认为贴近真实场景。
- 数据多样性提升超5000%，优于9个基线方法。
利用大语言模型生成高质量图表面临数据稀缺与人工标注成本高的挑战。构建包含指令、数据和代码的三元组需要专业知识，难以规模化。为此，我们提出无参考自动反馈生成框架C²，包括自动反馈提供者ChartAF和多样化的无参考数据集ChartUIE-8K。实验显示，74%受访者强烈偏好反馈后结果，10%表示偏好；在第二轮测试中，ChartAF超越9个基线模型。ChartUIE-8K相较基准数据集，查询量、数据集数量和图表类型分别提升5982%、1936%和91%。用户研究发现，94%参与者更青睐该数据集的查询内容，93%认为其符合实际使用场景。核心成果已开源，附大量可视化示例。
原文摘要 · Abstract (English)
Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \text{instruction}, \text{data}, \text{code} \rangle$ triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability challenge, we introduce a reference-free automatic feedback generator, which eliminates the need for costly human intervention. Our novel framework, C$^2$, consists of (1) an automatic feedback provider (ChartAF) and (2) a diverse, reference-free dataset (ChartUIE-8K). The results are compelling: in our first experiment, 74% of respondents strongly preferred, and 10% preferred, the results after feedback. The second post-feedback experiment demonstrates that ChartAF outperform nine baselines. Moreover, ChartUIE-8K significantly improves data diversity by increasing queries, datasets, and chart types by 5982%, 1936%, and 91%, respectively, over benchmarks. Finally, a study of LLM users revealed that 94% of participants preferred ChartUIE-8K's queries, with 93% deeming them aligned with real-world use cases. Core contributions are available as open-source at chartsquared.github.io, with ample qualitative examples.
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。