A comparison of customized GPTs and GPT-4o for self-medication knowledge: A feasibility study using the Japanese registered salesperson examination

This feasibility study demonstrates that minimal customization through reference materials upload can achieve performance improvements on knowledge-based assessments. However, examination performance represents only an indirect indicator of knowledge for self-medication support. Future research should evaluate LLMs performance in real-world case scenarios and assess practical utility and safety before implementation in consumer self-medication settings.