Fine-Tuning Methods for Large Language Models in Clinical Medicine by Supervised Fine-Tuning and Direct Preference Optimization: Comparative Evaluation

Thomas Savage   ¹ , MD ;   Stephen P Ma   ² , MD, PhD ;   Abdessalem Boukil   ³ , BS ;   Ekanath Rangan   ⁴ , MD ;   Vishwesh Patel   ⁵ , MBBS ;   Ivan Lopez   ^{4, 6} , BS ;   Jonathan Chen   ^{2, 6, 7, 8} , MD, PhD

¹ Division of Hospital Medicine, Perelman School of Medicine, Department of Medicine, University of Pennsylvania, Philadelphia, PA, United States

² Division of Hospital Medicine, Department of Medicine, Stanford Medicine, Palo Alto, CA, United States

³ Linguamind AI, Sousse, Tunisia

⁴ Department of Medicine, Stanford Medicine, Palo Alto, CA, United States

⁵ Department of Medicine, Saint Michael’s Medical Center, Newark, New Jersey, United States

⁶ Center for Biomedical Informatics Research, Stanford University, Palo Alto, CA, United States

⁷ Stanford Center for Biomedical Informatics Research, Palo Alto, CA, United States

⁸ Clinical Excellence Research Center, Stanford University, Palo Alto, CA, United States