自动直方图:利用语言模型进行文本数据集探索
Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
AI总结:
本文提出 AutoHistograms,一个利用大型语言模型自动识别文本数据集相关特征并生成直方图的可视化工具,用户研究验证其能帮助数据工作者快速探索数据并获得洞见。
摘要:
理解非结构化文本数据集一直十分困难,而随着大型语言模型(Large Language Models)的发展,这一问题变得愈发重要。数据工作者通常依赖数据集摘要,尤其是各种派生特征的分布。有些特征(如毒性或主题)与许多数据集相关,但许多有趣的特征是领域特定的:例如音乐数据集中的乐器和流派,或医学数据集中的疾病和症状。因此,数据工作者通常需要为每个数据集运行定制分析,这既繁琐又困难。我们提出了 AutoHistograms,一个利用大型语言模型的可视化工具。AutoHistograms 能够自动识别相关特征,以直方图形式对其进行可视化,并允许用户交互式地查询数据集中各类实体的类别,并创建新的直方图。在一项涉及 10 名数据工作者的用户研究(n=10)中,我们观察到参与者能够使用 AutoHistograms 快速识别洞见并探索数据,同时构想出广泛的适用用例。总体而言,该工具和用户研究为日益发展的 LLM 辅助意义构建工具领域做出了贡献。
英文摘要:
Making sense of unstructured text datasets is perennially difficult, yet increasingly relevant with Large Language Models. Data workers often rely on dataset summaries, especially distributions of various derived features. Some features, like toxicity or topics, are relevant to many datasets, but many interesting features are domain specific: instruments and genres for a music dataset, or diseases and symptoms for a medical dataset. Accordingly, data workers often run custom analyses for each dataset, which is cumbersome and difficult. We present AutoHistograms, a visualization tool leveragingLLMs. AutoHistograms automatically identifies relevant features, visualizes them with histograms, and allows the user to interactively query the dataset for categories of entities and create new histograms. In a user study with 10 data workers (n=10), we observe that participants can quickly identify insights and explore the data using AutoHistograms, and conceptualize a broad range of applicable use cases. Together, this tool and user study contributeto the growing field of LLM-assisted sensemaking tools.
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。