测试病理图像推理中证据是否真实支撑答案，发现高准确率模型仍可能不靠谱。
PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts
- 设计新评测基准，检验模型是否真从大图中找到证据
- 仅1.86%的预测在证据变换后保持一致，暴露现有模型依赖文本线索
- 适合关注医学AI可解释性与真实推理能力的研究者
全切片病理分析需整合跨完整病例的亿级像素视觉证据，但现有问答基准仅衡量最终答案准确率，易受语言先验干扰且无法验证预测是否基于实际组织切片。我们提出PathoArgus-Bench，包含4,913名患者的22,078道四选题，覆盖TCGA中15个项目的六种病理能力，分三个证据需求层级，并设定固定阅读预算，仅保留极小部分原始上下文。为隔离证据依赖性，引入ESG（证据状态四联体）：问题文本固定，目标WSI集被移动、替换或移除，要求预测一致。评估20个通用、医学及病理专用系统发现：即使GPT-5.6达到57.09%总体准确率与57.04%ESG准确率，其在483个四联体中仅正确完成19个（QExact 3.93%），表明行级准确率不能代表可靠证据支撑。我们还提出PathoArgus，一种基于问题相关性与空间覆盖率分配上下文的固定预算阅读器，达50.39%准确率，但QExact仅为1.86%，证明提升上下文获取并不等于实现稳定证据推理。该基准与诊断工具表明，获取有用上下文是必要前提，却远不充分，亟需从以答案为中心转向以证据为基础的评估范式。
原文摘要 · Abstract (English)
Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy--a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact--demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。