Star Light, Star Bright: Can Multimodal Models Parse an Astronomy Visual Question Answering Dataset Right?
Computer Science > Computer Vision and Pattern Recognition arXiv:2610.22474 (cs) [Submitted on 15 Oct 2026] Title: Star Light, Star Bright: Can Multimodal Models Parse an Astronomy Visual Question Answering Dataset Right? Authors: J. P. Naiman.
计算机科学 > 计算机视觉与模式识别 arXiv:2610.22474 (cs) [提交于 2026 年 10 月 15 日] 标题：星光，星亮：多模态模型能否正确解析天文视觉问答数据集？作者：J. P. Naiman。
Abstract: Figures are essential for scientific communication, and the field of Visual Question Answering (VQA) aims to test the figure understanding capabilities of large multimodal models (LMMs). Here, we investigate the accuracy of several low-cost LMMs on domain-specific VQA tasks for astronomical images of the sky.
摘要：图表对于科学交流至关重要，而视觉问答（VQA）领域旨在测试大型多模态模型（LMMs）的图表理解能力。在此，我们研究了几种低成本 LMM 在针对天文天空图像的特定领域 VQA 任务中的准确性。
As instrument for this task we build a domain-specific VQA dataset comprising 2001 partially-synthetic figures divided evenly between contour plots, real telescope images drawn from NASA’s SkyView, and “fake” sky images which share the axes and angular scales of the real images but draw their colors from a gaussian mixture model, alongside 47357 questions.
作为该任务的工具，我们构建了一个特定领域 VQA 数据集，包含 2001 张部分合成的图表，平均分为等高线图、取自 NASA SkyView 的真实望远镜图像，以及与真实图像共享坐标轴和角尺度的“伪”天空图像（其颜色取自高斯混合模型），并附带 47357 个问题。
Each figure is released as pristine and with realistic page-aging degradations mimicking the historical astronomical corpus. Testing three low-cost proprietary LMMs, we find models frequently fail to answer domain-specific questions at high accuracy.
每张图表均以原始状态发布，并带有模拟历史天文文献库中逼真的页面老化退化效果。在测试了三种低成本专有 LMM 后，我们发现模型经常无法以高准确度回答特定领域的问题。
An initial comparison with 104 human-verified, astrometrically tagged figures from historical journal publications shows similar median errors in angular extent. All code is available on GitHub: this https URL and dataset is available on HuggingFace: this https URL.
与来自历史期刊出版物的 104 张经人工验证且带有天体测量标签的图表进行的初步比较显示，角范围的中值误差相似。所有代码均可在 GitHub 上获取：此 https 链接；数据集可在 HuggingFace 上获取：此 https 链接。