{"id":560262,"date":"2023-05-23T14:59:02","date_gmt":"2023-05-23T18:59:02","guid":{"rendered":"https:\/\/www.rochester.edu\/newscenter\/?p=560262"},"modified":"2023-05-30T11:55:44","modified_gmt":"2023-05-30T15:55:44","slug":"large-language-models-gpt-4-chemistry-560262","status":"publish","type":"post","link":"https:\/\/www.rochester.edu\/newscenter\/large-language-models-gpt-4-chemistry-560262\/","title":{"rendered":"Large language models could be the catalyst for a new era of chemistry"},"content":{"rendered":"

Chemical engineer Andrew D. White explains why large language models like GPT-4 will open new frontiers for researchers.<\/h2>\n

Large language models like the one behind the popular ChatGPT could transform the future of chemistry, according to a researcher at the University of Rochester<\/a>. Andrew D. White<\/a>, an associate professor of chemical engineering<\/a>, outlines why he believes large language models (LLMs) represent the future of the field in a commentary published<\/a> by Nature Reviews Chemistry<\/em>.<\/p>\n

White\u2019s research group uses experiments, molecular simulations, and machine-learning to design new materials. He has been using early versions of GPT-4 since September 2022 as part of OpenAI\u2019s \u201cred team,\u201d<\/a> a group of researchers hired to help mitigate the risks of artificial intelligence models by testing the platform\u2019s capacity for harmful, illegal, or even unintended output. With the right guardrails in place, he expects GPT-4 and similar large language models to change not only how researchers connect their data, computer programs, and scientific literature, but also how they plan experiments.<\/p>\n

\u201cLike any emerging idea in chemistry, it will take time to see where LLMs will fit,\u201d writes White. He adds:<\/p>\n

They are already used in most modern reaction synthesis planner tools and have started seeing applications in explaining molecular properties\u2014but where might LLMs go next? I believe LLMs are about to be stapled to every tool in chemistry. Akin to the creation of the internet, it is a foundational technology that will accelerate how fast a chemist can learn and use computational tools.<\/p><\/blockquote>\n

White notes the need to overcome key challenges with LLMs, such as the hallucination problem (i.e., when AI platforms fabricate facts, quotes, citations, or other outputs), in order to realize their potential. But he argues this is an exciting time to reimagine tools and experiments in the field of chemistry, and that harnessing large language models will open new frontiers for researchers.<\/p>\n

\u201cClear communication in natural language is about to be the most valuable technical skill as we enter this new phase of chemistry,\u201d he writes.<\/p>\n