KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration

arXiv:2509.17037 · cs.AI · Submitted 2025-09-21 · Read on arXiv

cs.AI

Submitted: 2025-09-21

Updated: 2025-09-21

Comments: Accepted at EMNLP 2025 Findings

Journal ref: Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25761-25785, Suzhou, China. Association for Computational Linguistics

DOI: 10.18653/v1/2025.findings-emnlp.1405

Code: https://github.com/yajingyang/kahan

License: http://creativecommons.org/licenses/by/4.0/

The gist: We propose KAHAN, a knowledge-augmented hierarchical framework that systematically extracts insights from raw tabular data at entity, pairwise, group, and system levels.

Terminology

Abstract

We propose KAHAN, a knowledge-augmented hierarchical framework that systematically extracts insights from raw tabular data at entity, pairwise, group, and system levels. KAHAN uniquely leverages LLMs as domain experts to drive the analysis. On DataTales financial reporting benchmark, KAHAN outperforms existing approaches by over 20% on narrative quality (GPT-4o), maintains 98.2% factuality, and demonstrates practical utility in human evaluation. Our results reveal that knowledge quality drives model performance through distillation, hierarchical analysis benefits vary with market complexity, and the framework transfers effectively to healthcare domains. The data and code are available at https://github.com/yajingyang/kahan.

Sources

Related papers