Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Savage, Thomas, Ma, Stephen, Boukil, Abdessalem, Patel, Vishwesh, Rangan, Ekanath, Lopez, Ivan, Chen, Jonathan H
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916521463250944
author Savage, Thomas
Ma, Stephen
Boukil, Abdessalem
Patel, Vishwesh
Rangan, Ekanath
Lopez, Ivan
Chen, Jonathan H
author_facet Savage, Thomas
Ma, Stephen
Boukil, Abdessalem
Patel, Vishwesh
Rangan, Ekanath
Lopez, Ivan
Chen, Jonathan H
contents Large Language Model (LLM) fine tuning is underutilized in the field of medicine. Two of the most common methods of fine tuning are Supervised Fine Tuning (SFT) and Direct Preference Optimization (DPO), but there is little guidance informing users when to use either technique. In this investigation, we compare the performance of SFT and DPO for five common natural language tasks in medicine: Classification with text data, Classification with numeric data, Clinical Reasoning, Summarization, and Clinical Triage. We find that SFT alone is sufficient for Classification with text data, whereas DPO improves performance for the more complex tasks of Clinical Reasoning, Summarization and Clinical Triage. Our results establish the role and importance of DPO fine tuning within medicine, and consequently call attention to current software gaps that prevent widespread deployment of this technique.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12741
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization
Savage, Thomas
Ma, Stephen
Boukil, Abdessalem
Patel, Vishwesh
Rangan, Ekanath
Lopez, Ivan
Chen, Jonathan H
Computation and Language
Artificial Intelligence
Large Language Model (LLM) fine tuning is underutilized in the field of medicine. Two of the most common methods of fine tuning are Supervised Fine Tuning (SFT) and Direct Preference Optimization (DPO), but there is little guidance informing users when to use either technique. In this investigation, we compare the performance of SFT and DPO for five common natural language tasks in medicine: Classification with text data, Classification with numeric data, Clinical Reasoning, Summarization, and Clinical Triage. We find that SFT alone is sufficient for Classification with text data, whereas DPO improves performance for the more complex tasks of Clinical Reasoning, Summarization and Clinical Triage. Our results establish the role and importance of DPO fine tuning within medicine, and consequently call attention to current software gaps that prevent widespread deployment of this technique.
title Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.12741