SOTAVerified

DataTales: A Benchmark for Real-World Intelligent Data Narration

2024-10-23Code Available0· sign in to hype

Yajing Yang, Qian Liu, Min-Yen Kan

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We introduce DataTales, a novel benchmark designed to assess the proficiency of language models in data narration, a task crucial for transforming complex tabular data into accessible narratives. Existing benchmarks often fall short in capturing the requisite analytical complexity for practical applications. DataTales addresses this gap by offering 4.9k financial reports paired with corresponding market data, showcasing the demand for models to create clear narratives and analyze large datasets while understanding specialized terminology in the field. Our findings highlights the significant challenge that language models face in achieving the necessary precision and analytical depth for proficient data narration, suggesting promising avenues for future model development and evaluation methodologies.

Reproductions