KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration
This addresses the challenge of generating high-quality, factual narratives from financial data for analysts and stakeholders, though it appears incremental as it builds on existing hierarchical and knowledge-augmented approaches.
The paper tackles the problem of extracting insights from raw tabular financial data by proposing KAHAN, a knowledge-augmented hierarchical framework that uses LLMs as domain experts, resulting in over 20% improvement in narrative quality on a benchmark while maintaining 98.2% factuality.
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.