将复杂文档拆解为独立语义块，提升大模型对图文混合文档的抽取能力
Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments
- 将文档按语义切分为可复用的局部文本块，分块处理增强理解
- 在多个公开数据集上提升1-3%的F1分数，超越当前最佳方法
- 能推理未明确写出的信息，且对新格式文档有强适应性
从包含版式信息的图文混合文档（VRDs）中进行信息抽取是重要且研究充分的任务。传统非大模型方法依赖文本与几何信息联合训练，虽能标注实体或回答问题，但缺乏推理能力，无法推断未明示内容，且泛化性差。近期生成式大模型方法具备推理能力，但在陌生文档格式下难以理解版式线索，且在异构数据集上表现不具竞争力。本文提出BLOCKIE，一种新型大模型方法，将文档组织为局部、可复用的语义文本段（称为语义块），并独立处理。通过聚焦且更具泛化性的推理，该方法在公开VRD基准上实现1-3%的F1分数提升，对未见过的文档格式具有鲁棒性，并展现出从文档中提取隐含信息的能力。
原文摘要 · Abstract (English)
Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues from document layout especially in previously unseen document formats, and do not show competitive performance in heterogeneous VRD benchmark datasets. In this paper, we propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments called $\textit{semantic blocks}$, which are processed independently. Through focused and more generalizable reasoning,our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3% in F1 scores, is resilient to document formats previously not encountered and shows abilities to correctly extract information not explicitly present in documents.
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。