KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
KAHANI: Culturally-Nuanced Visual Storytelling Pipeline for Non-Western Cultures
Large Language Models (LLMs) and Text-To-Image (T2I) models have demonstrated the ability to generate compelling text and visual stories. However, their outputs are predominantly aligned with the sensibilities of the Glo…
Story GenerationVisual StorytellingKARNA at COIN Shared Task 1: Bidirectional Encoder Representations from Transformers with relational knowledge for machine comprehension with common sense
This paper describes our model for COmmonsense INference in Natural Language Processing (COIN) shared task 1: Commonsense Inference in Everyday Narrations. This paper explores the use of Bidirectional Encoder Representat…
Common Sense ReasoningReading ComprehensionMatrices with Gaussian noise: optimal estimates for singular subspace perturbation
The Davis-Kahan-Wedin $\sin \Theta$ theorem describes how the singular subspaces of a matrix change when subjected to a small perturbation. This classic result is sharp in the worst case scenario. In this paper, we prove…
Matrix CompletionNarrationDep: Narratives on Social Media For Automatic Depression Detection
Social media posts provide valuable insight into the narrative of users and their intentions, including providing an opportunity to automatically model whether a social media user is depressed or not. The challenge lies …
Depression DetectionVLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
Human daily activities can be concisely narrated as sequences of routine events (e.g., turning off an alarm) in video streams, forming an event vocabulary. Motivated by this, we introduce VLog, a novel video understandin…
EgoSchemaRetrievalVideo Understanding