Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Yajing, Deng, Tony, Kan, Min-Yen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.17037
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908549958860800
author Yang, Yajing
Deng, Tony
Kan, Min-Yen
author_facet Yang, Yajing
Deng, Tony
Kan, Min-Yen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration
Yang, Yajing
Deng, Tony
Kan, Min-Yen
Artificial Intelligence
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.
title KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration
topic Artificial Intelligence
url https://arxiv.org/abs/2509.17037