{"id":41887,"date":"2026-09-08T10:06:55","date_gmt":"2026-09-08T08:06:55","guid":{"rendered":"https:\/\/nr.no\/en\/?post_type=bc_project&p=41887"},"modified":"2026-09-08T13:51:13","modified_gmt":"2026-09-08T11:51:13","slug":"matsci-llm","status":"publish","type":"bc_project","link":"https:\/\/nr.no\/en\/projects\/matsci-llm\/","title":{"rendered":"Advancing materials science research with large language models (MatSci-LLM)"},"content":{"rendered":"\n
\n
\n

The MatSci-LLM project explores how large language models (LLMs) can become more useful for materials scientists. By adapting AI to specialised terminology and complex scientific data, we are helping researchers streamline information analysis, answer complex questions, and identify new directions for future research.<\/strong><\/p>\n\n\n\n

\"Close-up
Photo: Julia Koblitz \/ Unsplash.<\/figcaption><\/figure>\n\n\n\n

Materials scientists work with vast amounts of specialised information, including scientific papers, experimental data, phase diagrams, tables and crystal structures. Reviewing and connecting this information is time-consuming and leaves less time for experiments and scientific discovery. <\/p>\n\n\n\n

Although current AI systems are effective at processing text, the models still struggle with various types of structured data and scientific visualisations used in materials science.<\/p>\n\n\n\n

MatSci-LLM investigates how AI can support researchers at different stages of their work, from identifying patterns and using calculation tools to proposing hypotheses for further investigation. The project will also contribute to the development of AI research assistants and agent-based systems for scientific tasks, giving scientists better tools for investigating questions and testing new ideas.<\/p>\n\n\n\n

How we are applying LLMs to materials science<\/h2>\n\n\n\n

As a multidisciplinary project, MatSci-LLM brings together expertise in materials science, natural language processing and image analysis to support researchers at different stages of the research process. <\/p>\n\n\n\n

The project will:<\/p>\n\n\n\n