CLAug 23, 2025

SPORTSQL: An Interactive System for Real-Time Sports Reasoning and Visualization

arXiv:2508.17157v11 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis

This work addresses the need for non-expert users to interactively explore dynamic sports statistics, though it is incremental as it applies existing LLM and database techniques to a specific domain.

The authors tackled the problem of real-time sports data querying and visualization by developing SPORTSQL, a modular system that translates natural language questions into SQL for live Fantasy Premier League data, achieving performance evaluation on a new benchmark of 1,700+ queries.

We present a modular, interactive system, SPORTSQL, for natural language querying and visualization of dynamic sports data, with a focus on the English Premier League (EPL). The system translates user questions into executable SQL over a live, temporally indexed database constructed from real-time Fantasy Premier League (FPL) data. It supports both tabular and visual outputs, leveraging the symbolic reasoning capabilities of Large Language Models (LLMs) for query parsing, schema linking, and visualization selection. To evaluate system performance, we introduce the Dynamic Sport Question Answering benchmark (DSQABENCH), comprising 1,700+ queries annotated with SQL programs, gold answers, and database snapshots. Our demo highlights how non-expert users can seamlessly explore evolving sports statistics through a natural, conversational interface.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes