Architectural smells are design flaws in software systems that, if left unaddressed, can negatively impact maintainability and system evolution. This study investigates the use of large language models for detecting and explaining Hub-like Dependency architectural smells, a critical smell type characterized by components with numerous incoming and outgoing dependencies. The research leverages Google’s Gemini 1.5 Pro, comparing its performance to Arcan, a specialized architectural smells detection tool. The study analyzes 135 architectural smells across 39 open-source Java projects, including 100 hub-like dependency smells with varying severity levels and 35 non-hub-like dependency smells. Results show that the large language model achieve 100% recall but varying precision, with more detailed prompts improving detection performance from 64% to 82% for lower-severity smells. However, the model’s ability to generate human-understandable explanations remains limited, with only 49% of the generated explanations rated as satisfactory. These findings highlight both the potential and the current limitations of large language models in architectural smell detection, suggesting the importance of prompt design in enhancing their capabilities.