The field of large language models (LLMs) is rapidly evolving, with a growing focus on adapting these models to specialized applications and domains. Recent developments have highlighted the potential of LLMs to transform various industries, including geotechnical engineering, social simulation, and scientific communication. A key direction in this field is the development of methods for domain adaptation, which enable LLMs to be fine-tuned for specific tasks and domains. This has led to significant improvements in performance and efficiency, making LLMs more accessible and useful for a wide range of applications. Notable advancements include the use of LLMs for generating OpenAPI specifications, simulating social information propagation, and streamlining geotechnical workflows. While there are still challenges to be addressed, such as the uncanny valley of LLMs in social simulation, the overall trend is towards increased adoption and innovation in the use of LLMs for specialized applications. Noteworthy papers in this area include: OASBuilder, which introduces a novel framework for generating OpenAPI specifications from online API documentation using large language models. Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining presents a method for efficient deployment of small LLMs in enterprise applications. Text to model via SysML proposes a strategy for automated generation of dynamical system computational models from unstructured natural language text using System Modeling Language diagrams and Large Language Models.