Neurosymbolic Information Extraction from Transactional Documents

2025-12-10

AI Summary

Existing methods for information extraction from financial transaction documents suffer from poor zero-shot generalization and difficulty in enforcing arithmetic constraints (e.g., balance consistency, quantity conservation). Method: This paper proposes a neuro-symbolic fusion framework that leverages large language models (LLMs) to generate candidate extractions, augmented by a three-tier symbolic verification mechanism—syntactic, task-specific, and domain-specific—to rigorously enforce arithmetic consistency. It introduces the first structured schema tailored to transaction documents and enables symbolic-guided zero-shot knowledge distillation. Domain rules are tightly integrated with neural generation to enhance interpretability and cross-document generalization. Results: Evaluated on a re-annotated transaction dataset, the framework achieves significant improvements in F1 score and accuracy. Empirical results validate the effectiveness and robustness of this neuro-symbolic verification paradigm for financial document processing.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Neuro-Symbolic Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This paper presents a neurosymbolic framework for information extraction from documents, evaluated on transactional documents. We introduce a schema-based approach that integrates symbolic validation methods to enable more effective zero-shot output and knowledge distillation. The methodology uses language models to generate candidate extractions, which are then filtered through syntactic-, task-, and domain-level validation to ensure adherence to domain-specific arithmetic constraints. Our contributions include a comprehensive schema for transactional documents, relabeled datasets, and an approach for generating high-quality labels for knowledge distillation. Experimental results demonstrate significant improvements in $F_1$-scores and accuracy, highlighting the effectiveness of neurosymbolic validation in transactional document processing.

Problem

• Develops a neurosymbolic framework for transactional document information extraction
• Integrates symbolic validation to enhance zero-shot performance and knowledge distillation
• Ensures domain-specific arithmetic constraints through multi-level validation methods

Innovation

• Neurosymbolic framework integrates symbolic validation methods
• Schema-based approach enables effective zero-shot output and distillation
• Validation filters candidates through syntactic, task, and domain levels