零样本可视化：用用户提示轴探索文本语料

AI 摘要

该论文提出零样本可视化（ZSV）任务，允许用户用自然语言指定概念轴，将文本语料映射到对应概念坐标上进行可视化探索。作者构建了基准，比较嵌入相似度、直接语义判断和条件似然估计三类打分方法，发现基于下一词概率的打分在语义忠实度、分数保真度和计算成本间取得最佳权衡。研究还发现离题文档存在组合情感偏差，并给出构建端到端ZSV基线的实践指南。

正文节选

Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes Abstract We study the application of large language models (LLMs) to the visual exploration of textual corpora. We introduce zero-shot visualization (ZSV), a task in which users specify concepts in natural language and documents are mapped onto the corresponding concept axes for visualization. Building a ZSV system of practical value is non-trivial, as it requires choices at the intersection of feature functions, efficient i

发布时间：2026-10-07 12:00

抓取时间：2026-10-07 12:08

来源机构：arXiv