Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

  • 类型：arxiv
  • 标识：2603.28583
  • 链接：https://arxiv.org/abs/2603.28583
  • 主分类：agent
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework designed to unmask visual deception via a "skeptical" reasoning paradigm. Unlike holistic models, ChartCynics decouples perception from verification: a Diagnostic Vision Path captures structural anomalies (e.g., inverted axes) through strategic ROI cropping, while an OCR-Driven Data Path ensures numerical grounding. To resolve cross-modal conflicts, we introduce
  • OpenAlex ID：W7147719566
  • OpenAlex DOI：10.48550/arxiv.2603.28583
  • DOI：10.48550/arxiv.2603.28583
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2603.28583
  • OpenAlex更新：2026-07-19
  • 副分类：multimodal
  • 待LLM分类：否
  • 标题中文：Navigating the Mirage：面向鲁棒误导性图表问答的双路径 Agentic 框架
  • TLDR中文：尽管视觉-语言模型（VLMs）已取得成功，但误导性图表因欺骗性视觉结构与失真数据表示仍构成重大挑战。我们提出 ChartCynics，一个通过"怀疑式"推理范式揭露视觉欺骗的 Agentic 双路径框架。与整体化模型不同，ChartCynics 将感知与验证解耦：诊断式视觉路径通过策略性 ROI 裁剪捕获结构异常（如倒置坐标轴），OCR 驱动数据路径确保数值根植性。为解决跨模态冲突，我们提出
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-16-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]