DataTales: A Benchmark for Real-World Intelligent Data Narration
This addresses the gap in practical data narration benchmarks for financial applications, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating language models' ability to narrate complex tabular data by introducing DataTales, a benchmark with 4.9k financial reports and market data, and found that models struggle with precision and analytical depth in this task.
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.