arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2404.17136cs.DBcs.AIcs.CL
收藏

基于大型语言模型的自然语言自动化数据可视化：一项探索性研究

Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study

Huazhong University of Science and Technology（华中科技大学）；Chongqing University（重庆大学）；University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）

Yang Wu, Yao Wan, Hongyu Zhang, Yulei Sui, Wucai Wei, Wei Zhao, Guandong Xu, Hai Jin

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文探索大型语言模型在自然语言到可视化任务中的潜力，提出将表格数据转换为程序并考虑表格模式构建提示，实验表明LLMs优于基线方法，且迭代更新策略能进一步提升性能。

摘要：

自然语言到可视化（NL2Vis）任务旨在将自然语言描述转换为基于基础表格的可视化表示，使用户能够从海量数据中获取洞察。近期，许多基于深度学习的NL2Vis方法被开发出来。尽管这些方法付出了相当大的努力，但在可视化来自未见过的数据库或跨多个表格的数据时仍存在挑战。受大型语言模型（LLMs）卓越生成能力的启发，本文进行了一项实证研究以评估其在生成可视化方面的潜力，并探索上下文学习提示在增强该任务中的有效性。具体而言，我们首先探索将结构化表格数据转换为序列文本提示的方法，以便将其输入LLMs，并分析哪些表格内容对NL2Vis贡献最大。研究结果表明，将结构化表格数据转换为程序是有效的，且在构建提示时考虑表格模式至关重要。此外，我们使用NL2Vis基准（即nvBench）评估了两类LLMs：微调模型（如T5-Small）和仅推理模型（如GPT-3.5），并与最先进方法进行了对比。实验结果显示LLMs优于基线方法，其中仅推理模型持续展现出性能提升，在通过上下文学习提供特定少样本演示时，有时甚至超越微调模型。最后，我们分析了LLMs在NL2Vis中失败的情况，并提出使用思维链、角色扮演和代码解释器等策略迭代更新结果。实验结果证实了迭代更新的有效性，为未来研究提供了巨大潜力。

英文摘要：

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for enhancing this task. In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis. Our findings suggest that transforming structured tabular data into programs is effective, and it is essential to consider the table schema when formulating prompts. Furthermore, we evaluate two types of LLMs: finetuned models (e.g., T5-Small) and inference-only models (e.g., GPT-3.5), against state-of-the-art methods, using the NL2Vis benchmarks (i.e., nvBench). The experimental results reveal that LLMs outperform baselines, with inference-only models consistently exhibiting performance improvements, at times even surpassing fine-tuned models when provided with certain few-shot demonstrations through in-context learning. Finally, we analyze when the LLMs fail in NL2Vis, and propose to iteratively update the results using strategies such as chain-of-thought, role-playing, and code-interpreter. The experimental results confirm the efficacy of iterative updates and hold great potential for future study.

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。

↑