SportQA: A Benchmark for Sports Understanding in Large Language Models

TL;DR

SportQA is a new benchmark with over 70,000 questions designed to evaluate and improve large language models' understanding of sports, from basic facts to complex reasoning, highlighting current limitations in LLMs' sports comprehension.

Contribution

We introduce SportQA, the first comprehensive sports knowledge benchmark for LLMs, enabling detailed assessment of their reasoning and understanding in sports contexts.

Findings

LLMs perform well on basic sports facts

LLMs struggle with complex, scenario-based sports reasoning

SportQA reveals gaps in current LLM capabilities

Abstract

A deep understanding of sports, a field rich in strategic and dynamic content, is crucial for advancing Natural Language Processing (NLP). This holds particular significance in the context of evaluating and advancing Large Language Models (LLMs), given the existing gap in specialized benchmarks. To bridge this gap, we introduce SportQA, a novel benchmark specifically designed for evaluating LLMs in the context of sports understanding. SportQA encompasses over 70,000 multiple-choice questions across three distinct difficulty levels, each targeting different aspects of sports knowledge from basic historical facts to intricate, scenario-based reasoning tasks. We conducted a thorough evaluation of prevalent LLMs, mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting. Our results reveal that while LLMs exhibit competent performance in basic sports knowledge, they struggle with more complex, scenario-based sports reasoning, lagging behind human expertise. The introduction of SportQA marks a significant step forward in NLP, offering a tool for assessing and enhancing sports understanding in LLMs.