SAIL: Sample-Centric In-Context Learning for Document Information Extraction

Document Information Extraction (DIE) aims to extract structured information from Visually Rich Documents (VRDs). Previous full-training approaches have demonstrated strong performance but may struggle with generalization to unseen data. In contrast, training-free methods leverage powerful pre-trained models like Large Language Models (LLMs) to address various downstream tasks with only a few examples. Nonetheless, training-free methods for DIE encounter two primary challenges: (1) understanding the complex relationship between layout and textual elements in VRDs, and (2) providing accurate guidance to pre-trained models. To address these challenges, we propose SAmple-centric In-context Learning (SAIL). SAIL introduces a fine-grained entity-level textual similarity to facilitate in-depth text analysis by LLMs and incorporates layout similarity to enhance the analysis of layouts in VRDs. Moreover, SAIL formulates a unified In-Context Learning (ICL) prompt template for various sample-centric examples, enabling tailored prompts that deliver precise guidance to pre-trained models for each sample. Extensive experiments on FUNSD, CORD, and SROIE benchmarks with various base models (e.g., LLMs) indicate that our SAIL outperforms training-free baselines, even closer to the full-training methods, showing the superiority and generalization of our method.

Authors

• Jinyu Zhang Harbin Institute of Technology
• Zhiyuan You The Chinese University of Hong Kong
• Jize Wang Shanghai Jiao Tong University
• Xinyi Le School of Electronics Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China

Keywords

No keywords are indexed for this paper.