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

arXiv: https://arxiv.org/abs/2509.17037 · HTML: https://mlsanity.com/paper/2509.17037/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 64 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Is GPT-4 a Good Data Analyst?](https://mlsanity.com/paper/2305.15038/) (2023)
- [Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.10708/) (2025)
- [DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts](https://mlsanity.com/paper/2408.05346/) (2024)
- [Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams](https://mlsanity.com/paper/2310.08678/) (2023)
- [Characterizing Automated Data Insights](https://mlsanity.com/paper/2008.13060/) (2020)
- [DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation](https://mlsanity.com/paper/2405.15329/) (2024)
- [XInsight: eXplainable Data Analysis Through The Lens of Causality](https://mlsanity.com/paper/2207.12718/) (2022)
- [Leveraging Foundation Models for Crafting Narrative Visualization: A Survey](https://mlsanity.com/paper/2401.14010/) (2024)
- [Neural Data-to-Text Generation with Dynamic Content Planning](https://mlsanity.com/paper/2004.07426/) (2020)
- [DataTales: A Benchmark for Real-World Intelligent Data Narration](https://mlsanity.com/paper/2410.17859/) (2024)

## Built on by (most cited first, 1 of 1)

- [AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation](https://mlsanity.com/paper/2609.00818/) (2026)

## Abstract (arXiv)

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.