iconLogo
Published:2025/8/23 0:42:43

グラフ分析AI、透明度爆上げ!RADAR爆誕✨

  1. 超要約: グラフ分析AIの「なんで?」を解決!根拠を可視化するフレームワークRADARがすごい🎉

  2. ギャル的キラキラポイント✨

    • ● グラフ分析AIの「説明できない」を解決!まるで推しのプレゼンみたいに分かりやすくするよ💖
    • ● グラフのどの部分を見てAIが判断したか、一発で分かる!「ここ見てたんだ!」って感動✨
    • ● ビジネス、医療、教育…色んな分野で大活躍!AIの信頼度が爆上がりする予感😍
  3. 詳細解説

続きは「らくらく論文」アプリで

RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis

Anku Rani / Aparna Garimella / Apoorv Saxena / Balaji Vasan Srinivasan / Paul Pu Liang

Data visualizations like charts are fundamental tools for quantitative analysis and decision-making across fields, requiring accurate interpretation and mathematical reasoning. The emergence of Multimodal Large Language Models (MLLMs) offers promising capabilities for automated visual data analysis, such as processing charts, answering questions, and generating summaries. However, they provide no visibility into which parts of the visual data informed their conclusions; this black-box nature poses significant challenges to real-world trust and adoption. In this paper, we take the first major step towards evaluating and enhancing the capabilities of MLLMs to attribute their reasoning process by highlighting the specific regions in charts and graphs that justify model answers. To this end, we contribute RADAR, a semi-automatic approach to obtain a benchmark dataset comprising 17,819 diverse samples with charts, questions, reasoning steps, and attribution annotations. We also introduce a method that provides attribution for chart-based mathematical reasoning. Experimental results demonstrate that our reasoning-guided approach improves attribution accuracy by 15% compared to baseline methods, and enhanced attribution capabilities translate to stronger answer generation, achieving an average BERTScore of $\sim$ 0.90, indicating high alignment with ground truth responses. This advancement represents a significant step toward more interpretable and trustworthy chart analysis systems, enabling users to verify and understand model decisions through reasoning and attribution.

cs / cs.AI