Dartmouth's Geisel School of Medicine Runs AI Patient Actor 2.0, Constraining a Mixture of LLMs With Educator-Authored Patient Profiles, Configurations and Rubrics Across 52 Languages
Dartmouth's NILE Laboratory at the Geisel School of Medicine operates AI Patient Actor 2.0, an open-access platform where health-professions trainees interview simulated patients by text or emotive voice in 52 languages. A mixture of LLMs plays the patient, drafts cases and scores encounters, but every response is constrained by educator-authored Patient Profiles, Configurations and faculty rubrics. Students get rubric-scored feedback after each encounter, with prosody analysis for voice sessions.