Computer Science

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

Y. Zhang, X. Chen, et al.

This paper provides a comprehensive survey of over 260 scientific LLMs, unveiling cross-field and cross-modal connections in architectures and pre-training techniques, summarizing pre-training datasets and evaluation tasks for each field and modality, and examining deployments that accelerate scientific discovery. Resources are available at https://github.com/yuzhimanhua/Awesome-Scientific-Language-Models. This research was conducted by Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, and Jiawei Han.