Our study investigates the efficacy of ChatGPT-assisted learning in enhancing the understanding of Advanced Driver Assistance Systems (ADAS) functionalities, comparing it against conventional paper-based learning methods. By employing multiple-choice questionnaires and the NASA Task Load Index to evaluate comprehension and cognitive load, we aimed to assess the impact of interactive Large Language Model (LLM)-driven learning on knowledge acquisition and learner satisfaction. Our findings indicate that participants who engaged with ChatGPT-based training scored higher (on average 11% higher) in correctness and experienced lower cognitive and physical demands, suggesting a more effective and less stressful learning process. This study contributes by highlighting ChatGPT's potential to accommodate a wide range of learning preferences and improve the comprehension of complex systems or topics. This adaptability was evident across diverse educational backgrounds among young adult participants, showcasing the tool's ability to bridge knowledge gaps more efficiently than conventional methods. Our research advocates the integration of LLM-driven tools in educational and policy-making frameworks to improve the effectiveness of teaching complex systems. This suggests broader applicability and necessitates further investigation into the scalability and effectiveness of ChatGPT-based training across different demographics and learning domains, potentially informing future educational strategies.