Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917647754461184 |
|---|---|
| author | Christophe, Clément Kanithi, Praveen K Munjal, Prateek Raha, Tathagata Hayat, Nasir Rajan, Ronnie Al-Mahrooqi, Ahmed Gupta, Avani Salman, Muhammad Umar Gosal, Gurpreet Kanakiya, Bhargav Chen, Charles Vassilieva, Natalia Amor, Boulbaba Ben Pimentel, Marco AF Khan, Shadab |
| author_facet | Christophe, Clément Kanithi, Praveen K Munjal, Prateek Raha, Tathagata Hayat, Nasir Rajan, Ronnie Al-Mahrooqi, Ahmed Gupta, Avani Salman, Muhammad Umar Gosal, Gurpreet Kanakiya, Bhargav Chen, Charles Vassilieva, Natalia Amor, Boulbaba Ben Pimentel, Marco AF Khan, Shadab |
| contents | This study presents a comprehensive analysis and comparison of two predominant fine-tuning methodologies - full-parameter fine-tuning and parameter-efficient tuning - within the context of medical Large Language Models (LLMs). We developed and refined a series of LLMs, based on the Llama-2 architecture, specifically designed to enhance medical knowledge retrieval, reasoning, and question-answering capabilities. Our experiments systematically evaluate the effectiveness of these tuning strategies across various well-known medical benchmarks. Notably, our medical LLM Med42 showed an accuracy level of 72% on the US Medical Licensing Examination (USMLE) datasets, setting a new standard in performance for openly available medical LLMs. Through this comparative analysis, we aim to identify the most effective and efficient method for fine-tuning LLMs in the medical domain, thereby contributing significantly to the advancement of AI-driven healthcare applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14779 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches Christophe, Clément Kanithi, Praveen K Munjal, Prateek Raha, Tathagata Hayat, Nasir Rajan, Ronnie Al-Mahrooqi, Ahmed Gupta, Avani Salman, Muhammad Umar Gosal, Gurpreet Kanakiya, Bhargav Chen, Charles Vassilieva, Natalia Amor, Boulbaba Ben Pimentel, Marco AF Khan, Shadab Computation and Language This study presents a comprehensive analysis and comparison of two predominant fine-tuning methodologies - full-parameter fine-tuning and parameter-efficient tuning - within the context of medical Large Language Models (LLMs). We developed and refined a series of LLMs, based on the Llama-2 architecture, specifically designed to enhance medical knowledge retrieval, reasoning, and question-answering capabilities. Our experiments systematically evaluate the effectiveness of these tuning strategies across various well-known medical benchmarks. Notably, our medical LLM Med42 showed an accuracy level of 72% on the US Medical Licensing Examination (USMLE) datasets, setting a new standard in performance for openly available medical LLMs. Through this comparative analysis, we aim to identify the most effective and efficient method for fine-tuning LLMs in the medical domain, thereby contributing significantly to the advancement of AI-driven healthcare applications. |
| title | Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.14779 |