Laser 3D scanning technology rapidly acquires point cloud data of target surfaces, including spatial point coordinates that describe the geometric features of the target and laser reflectance intensity that characterizes the material's reflectivity. The application of automatic semantic segmentation techniques for 3D point clouds in geological exploration research lays the foundation for depicting regional geological features. To demonstrate the recent advancements of 3D laser scanning technology in large-scale semantic segmentation within geological scenarios, firstly, photogrammetry and LiDAR as two methods for acquiring 3D point clouds were compared, highlighting the advantages of LiDAR in terms of accuracy, versatility, and insensitivity to lighting conditions. By elucidating the principles of lithological semantic segmentation, a comprehensive review and summary of recent methods based on geometric or intensity features were provided. Common large-scale point cloud datasets and evaluation metrics were introduced, and the segmentation performance of different algorithms was compared. Finally, the limitations of existing methods were summarized, and future research directions for lithological semantic segmentation tasks were outlined.