论文标题
使用大型语言模型为数据可视化生成引人入胜的字幕
Using Large Language Models to Generate Engaging Captions for Data Visualizations
论文作者
论文摘要
为数据可视化创建引人注目的字幕一直是一个长期的挑战。可视化研究人员通常在新闻报道中没有受过训练，因此在以下数据可视化下放置的字幕往往不会过于吸引人，而只是坚持对数据的基本观察。在这项工作中，我们探讨了新兴的大型语言模型（LLM）提供的机会，这些模型（LLM）使用复杂的深度学习技术来产生类似人类的散文。我们问，这些功能强大的软件设备是否旨在为散点图（例如散点图）产生引人入胜的字幕。事实证明，关键挑战在于为LLM设计最有效的提示，该任务称为提示工程。我们使用流行的LLM GPT-3进行了首次实验报告，并提供了一些有希望的结果。
Creating compelling captions for data visualizations has been a longstanding challenge. Visualization researchers are typically untrained in journalistic reporting and hence the captions that are placed below data visualizations tend to be not overly engaging and rather just stick to basic observations about the data. In this work we explore the opportunities offered by the newly emerging crop of large language models (LLM) which use sophisticated deep learning technology to produce human-like prose. We ask, can these powerful software devices be purposed to produce engaging captions for generic data visualizations like a scatterplot. It turns out that the key challenge lies in designing the most effective prompt for the LLM, a task called prompt engineering. We report on first experiments using the popular LLM GPT-3 and deliver some promising results.
