X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model

arXiv:2404.06332v1 Announce Type: new
Abstract: The rapid advancement of artificial intelligence has led to significant improvements in automated decision-making. However, the increased performance of models often comes at the cost of explainability and transparency of their decision-making processes. In this paper, we investigate the capabilities of large language models to explain decisions, using football refereeing as a testing ground, given its decision complexity and subjectivity. We introduce the Explainable Video Assistant Referee System, X-VARS, a multi-modal large language model designed …

abstract advancement artificial artificial intelligence arxiv automated capabilities cost cs.cv decision explainability football however improvements intelligence language language model language models large language large language model large language models making modal multi-modal paper performance processes transparency type