Lung cancer is a leading cause of cancer-related morbidity and mortality worldwide. Coupled with the substantial workload, the clinical management of lung cancer is challenged by the critical need to efficiently and accurately process increasingly complex medical information. In recent years, large language model technology has undergone explosive development, demonstrating unique advantages in handling complex medical data by leveraging its powerful natural language processing capabilities, and its application value in the field of lung cancer diagnosis and treatment is continuously increasing. This article reviews the research progress and applications of large language models in assisting with lung cancer diagnosis, tumor feature extraction, staging, analysis of disease progression and outcomes, treatment recommendations, clinical documentation generation, and patient medical education. We further analyze the current challenges and opportunities, and provide an outlook on the future development of specialized large language models for lung cancer.