AI public lecture

March 1, 9:00 am

Join the MOOVE (and get your own chatbot)

Community-driven Massive Online Open Validation and Evaluation for Continuous Real-World Alignment in Medical Chatbots.

Large language models (LLMs, i.e. chatbots) have the potential to democratize access to medical knowledge. Unfortunately, the enormous potential of these models is either locked behind commercial/research licenses, limited in scale, or not generalizable to underserved populations.

To address this issue, we developed Meditron-70B, currently the worldโ€™s best-performing fully open-source chatbot for medicine, trained on carefully curated clinical practice guidelines from diverse settings.

However, the performance of these chatbots is commonly measured on medical exam questions, which does not adequately evaluate real-world clinical utility and safety.

In this talk, I invite the UON/Kenyatta National Hospital clinical community to put Meditron to the test. I introduce the MOOVE (Massive Online Open Validation and Evaluation) platform that allows clinicians to validate the real-world performance of Meditron in terms of helpfulness, harmlessness, bias, trust, and safety. In return for this rigorous validation, participants can get their own chatbot, adapted to their preferences and specialty.