Institution profile

Shift Technology

Industry researcheurope · fr
Official website
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Neurosymbolic Information Extraction from Transactional Documents

Dec 10, 2025

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.

0 citationsRead paper
Recent publications

Latest Papers

Neurosymbolic Information Extraction from Transactional Documents

Dec 10, 2025

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.

0 citationsRead paper