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

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.

Yajing Yang

IPP Doctoral Student (Aug ‘20)
Co-Supervised by Kelvin Koa and Yunshan Ma
Research Achievement Award (RAA, ‘25)

PhD Candidate August 2020 Intake

Min-Yen Kan

Associate Professor

WING lead; interests include Digital Libraries, Information Retrieval and Natural Language Processing.