Recent advances in Quadruple Aspect-Based Sentiment Analysis (Quad-ABSA) have heavily relied on datasets from SemEval challenges, which raises concerns regarding the generalizability of these models across diverse domains. This study addresses this limitation by introducing a novel dataset specifically tailored to the hospitality sector, offering a unique benchmark to evaluate Quad-ABSA models. Our experiments reveal a notable gap: while existing models perform well with SemEval datasets, they fail to maintain their effectiveness when applied to our new domain-specific dataset. This underperformance highlights the critical importance of understanding dataset nuances, including domain-specific characteristics and annotation quality, which significantly influence model performance and generalization. Our research highlights the necessity for broader evaluations of Quad-ABSA models, advocating for the development and utilization of diverse and high-quality datasets to ensure robust and versatile sentiment analysis solutions.