Presentation Information

[19p-A21-5]Large-scale language model capable of processing in Japanese and potential for experimental research

〇Kan Hatakeyama1 (1.Tokyo Tech.)
PDF DownloadDownload PDF

Keywords:

Materials informatics,Generative AI

The emergence of large language models (LLMs), exemplified by GPT-4, has increased the potential to integrate various types of unstructured data, such as text, into the field of Materials Informatics (MI). LLMs equipped with multimodal capabilities, like processing images, can handle information corresponding to human thought and senses, raising expectations for analyzing diverse research data within the framework of data science. This presentation introduces the development status of LLMs that can serve as inference bases for autonomous research and discusses use cases of deploying multimodal LLMs in chemical experiments.

Comment

To browse or post comments, you must log in.Log in