Lune

EMNLP Findings2025

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

Yajing Yang, Tony Deng, Min-Yen Kan

Abstract

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

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Adapting Large Language Models via Reading Comprehension cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  3. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  4. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text GenerationSewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis et al.EMNLP 2023 · 225 citations
  5. Adapting Large Language Models via Reading ComprehensionDaixuan Cheng, Shaohan Huang, Furu WeiICLR 2024 · 146 citations

Related papers

  1. DataTales: A Benchmark for Real-World Intelligent Data NarrationYajing Yang, Qian Liu, Min-Yen KanEMNLP 2024 · 3 citations
  2. Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic GraphLirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang et al.ACL 2026
  3. AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data ScienceAn Luo, Xun Xian, Jin Du, Fangqiao Tian et al.EMNLP Findings 2025 · 2 citations
  4. MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular DataYaobin Ling, Xiaoqian Jiang, Yejin KimACL Findings 2026 · 3 citations
  5. TabReX: Tabular Referenceless eXplainable EvaluationTejas Anvekar, Junha Park, Aparna Garimella, Vivek GuptaACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines