DataTales: A Benchmark for Real-World Intelligent Data Narration
Yang, Yajing, Liu, Qian, Kan, Min-Yen
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-23-2024
- Country:
- Asia
- China (0.04)
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Singapore (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- Europe
- Austria (0.04)
- Monaco (0.04)
- Ukraine (0.04)
- United Kingdom (0.14)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States
- Louisiana > Orleans Parish
- New Orleans (0.04)
- New York > New York County
- New York City (0.14)
- Pennsylvania (0.04)
- Louisiana > Orleans Parish
- Canada > Ontario
- Asia
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.71)
- Natural Language
- Chatbot (0.71)
- Large Language Model (1.00)
- Text Processing (1.00)
- Machine Learning > Neural Networks
- Communications (1.00)
- Data Science (1.00)
- Artificial Intelligence
- Information Technology