PulseAugur
中
实时 08:50:47
Italiano(IT) DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

新的DataVista基准揭示多模态大语言模型在数据视频理解方面存在困难

研究人员推出了DataVista,这是首个旨在评估多模态大语言模型(MLLMs)数据视频理解能力的数据集。该数据集包含961个真实世界的数据视频和超过6700个问题,旨在评估数据感知、时间推理和叙事理解能力。对19个MLLMs的评估显示,即使是表现最好的Gemini-3.1 Pro,准确率也仅为70.0%,远低于人类专家水平,在因果推理和叙事理解方面存在明显不足。研究还发现,增加帧数和添加字幕的改进有限,尤其是在叙事理解方面,并指出了图表解读和证据判断方面的常见失败模式。 AI

影响 凸显了当前MLLMs在专业数据解读任务中的局限性,表明需要改进多模态推理能力。

排序理由 该集群包含一篇介绍新AI模型评估基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的DataVista基准揭示多模态大语言模型在数据视频理解方面存在困难

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇介绍新AI模型评估基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 Italiano(IT) · Yupeng Xie, Zhenyang Wang, Jiayi Zhu, Yinghao Tang, Zhouan Shen, Yiyu Chen, Yuyu Luo ·

    DataVista:诊断多模态大语言模型的数据视频理解能力

    arXiv:2610.11993v1 Announce Type: cross Abstract: Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video understanding, data video understanding places greater emphasi…