AI 中文总结
HierDoc是分层证据路由框架，将长文档视觉问答的页与区域选择整合为连续两阶段，在开放权重系统中达SOTA，使LongDocURL提升16.87%，区域证据可显著提升单页系统性能。
AI 中文摘要
多页文档视觉问答需要在页级和区域级定位稀疏证据。现有方法通常侧重其中一个层级：以页为中心的方法聚焦页获取，区域操作主要作为导航辅助；以区域为中心的方法则假设相关页已提供。因此，页和区域选择相互脱节，未形成连续的证据决策。我们提出HierDoc，这是一个分层证据路由框架，将长文档证据获取表述为从页到区域的两阶段集预测。页策略从完整文档中选择证据页，对这些页解析语义元素后，区域策略选择传递给下游答案模型的元素。这两种与答案无关的策略均采用分阶段的GRPO优化，使用粒度特定的结构化集奖励。答案模型接收选定的完整页、选定的区域裁剪内容及OCR或表格文本，在保留全局上下文的同时突出细粒度证据。在评估基准中，HierDoc在开放权重系统中达到SOTA或具有竞争力的性能，较最强已报道的开放权重基线，使LongDocURL提升了16.87%。受控消融实验进一步表明，选定的区域证据使仅用页的系统的准确率和F1分别提升5.51%和4.82%。这些结果证明，将粗粒度页路由和细粒度区域路由组织为统一证据获取过程的连续、单独优化阶段具有益处。
英文摘要
Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphasize one level over the other: page-centric methods focus on page acquisition, with region operations serving mainly as navigation aids, whereas region-centric methods assume that the relevant pages have already been supplied. Consequently, page and region selection remain disconnected rather than forming successive evidence decisions. We propose HierDoc, a hierarchical evidence-routing framework that formulates long-document evidence acquisition as two-stage set prediction from pages to regions. A page policy selects evidence pages from the full document; these pages are then parsed for semantic elements, after which a region policy selects the elements passed to a downstream answer model. Both answer-agnostic policies are optimized with stage-wise GRPO using granularity-specific structured-set rewards. The answer model receives selected full pages together with selected region crops and OCR or table text, preserving global context while emphasizing fine-grained evidence. Across the evaluated benchmarks, HierDoc achieves state-of-the-art or competitive performance among open-weight systems, improving LongDocURL by 16.87% relative to the strongest reported open-weight baseline. Controlled ablations further show that selected regional evidence improves the page-only system in accuracy and F1 by 5.51% and 4.82%, respectively. These results demonstrate the benefit of organizing coarse page routing and fine-grained region routing as successive, separately optimized stages of a unified evidence-acquisition process.
Comments15 pages, 4 figures; includes supplementary material
