Can you help ChatGPT get an ‘A’ in organic chemistry? Teaching effective prompting of large language models for reaction prediction

Generative artificial intelligence (AI) tools such as large language models (LLMs) have become ubiquitous in everyday life, and are also increasingly finding applications in the chemical sciences. Although LLMs have achieved impressive performance on many chemistry tasks, optimal performance requires proper use, including appropriate prompting techniques. However, chemistry students are not generally taught strategies for effective LLM usage. Here we report an activity that introduces organic chemistry students to the use of LLMs like ChatGPT for predicting the outcome of chemical reactions, focusing on the types of alkene addition reactions taught in introductory organic chemistry courses. This activity exposes students to molecular representations, digitization of chemical reactions, best practices for machine learning, and generalizable LLM prompting strategies, namely the 5S approach and in-context learning. We tested this activity with chemistry students in the USA and in Austria and evaluated the activity through anonymous pre- and post-lab surveys. Survey data revealed that students felt that they achieved their learning goals and that they found the activity enjoyable. As chemistry students will inevitably interact with LLMs in their future careers, it is important to teach best practices for effective and critical use of these tools in the context of chemistry.