arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.14047cs.CLcs.AIcs.HC
收藏

使用大语言模型为数据可视化生成引人入胜的标题

Using Large Language Models to Generate Engaging Captions for Data Visualizations

Rochester Institute of Technology(罗切斯特理工学院);Stony Brook University(石溪大学)

Ashley Liew, Klaus Mueller

摘要:

为数据可视化创建引人注目的标题一直是一个长期的挑战。可视化研究人员通常没有接受过新闻报道的培训,因此放在数据可视化下面的标题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,我们探索了新出现的大语言模型(LLM)的作物,使用复杂的深度学习技术,以产生类似人类的散文提供的机会。我们问,这些强大的软件设备能否为散点图等通用数据可视化生成引人入胜的标题。事实证明,关键的挑战在于为LLM设计最有效的提示,这项任务称为提示工程。我们报告了使用流行的LLM GPT-3的第一次实验,并提供了一些有希望的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑