SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs
This work addresses the problem of evaluating numerical reasoning and information fusion in LLMs for researchers, but it is incremental as it builds on existing benchmarks with new tasks.
The paper tackled the challenge of blending text and numerical data in LLMs by introducing SportsMetrics, a benchmark with four novel tasks using sports data, and found that LLMs struggle with adversarial scenarios like new rules and scrambled narratives in NBA and NFL games.
Large language models hold significant potential for integrating various data types, such as text documents and database records, for advanced analytics. However, blending text and numerical data presents substantial challenges. LLMs need to process and cross-reference entities and numbers, handle data inconsistencies and redundancies, and develop planning capabilities such as building a working memory for managing complex data queries. In this paper, we introduce four novel tasks centered around sports data analytics to evaluate the numerical reasoning and information fusion capabilities of LLMs. These tasks involve providing LLMs with detailed, play-by-play sports game descriptions, then challenging them with adversarial scenarios such as new game rules, longer durations, scrambled narratives, and analyzing key statistics in game summaries. We conduct extensive experiments on NBA and NFL games to assess the performance of LLMs on these tasks. Our benchmark, SportsMetrics, introduces a new mechanism for assessing LLMs' numerical reasoning and fusion skills.