Innovation
Methods, ideas, or system contributions that make the work stand out.
end-to-end agentic parsing system
vision-language model
homoglyph-aware contrastive learning
multi-stage reinforcement learning
human-in-the-loop Data Factory
FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks
🤖 AI Summary
为解决金融文档解析的准确性与一致性问题，提出FinixDoc系统，采用4B级视觉-语言模型及领域适应训练方法，并构建了评估基准FinixDocBench。
📝 Abstract
Financial document parsing requires accuracy, structural consistency, and verifiability that current benchmarks often fail to reflect. We present FinixDoc, an end-to-end agentic parsing system for real-world financial documents, with FinixDoc-VL, a 4B-scale vision-language model built on Qwen3-VL-4B, as its core parser. To characterize the gap between benchmark and deployment performance, we introduce a Document Parsing Capability Matrix organized along two practical axes: visual quality and document scale. Guided by this matrix, FinixDoc-VL is trained with a domain-adapted recipe combining homoglyph-aware contrastive learning and multi-stage reinforcement learning with composite domain-specific rewards. To better leverage our accumulated advantage in low-quality financial-document data and support large-scale, high-quality data production, we further build a human-in-the-loop Data Factory pipeline with confidence-aware expert review. For evaluation, we construct FinixDocBench, a financial-domain evaluation suite covering digital-native, camera-captured, ultra-large-page, and internal-workflow scenarios, with a compliance-reviewed subset released alongside this technical report. On its main subsets, FinixDoc-VL achieves the highest overall score (81.43) among evaluated baselines, outperforming the next-best open-source model by 5.13 points, with the largest gains on internal financial workflows (FinixInner: 84.08 vs. 78.73).
🔎 Similar Papers
2024-09-08arXiv.orgCitations: 5
