Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.01040 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910289620893696 |
|---|---|
| author | Li, Qiang Yang, Xiaoyan Wang, Haowen Wang, Qin Liu, Lei Wang, Junjie Zhang, Yang Chu, Mingyuan Hu, Sen Chen, Yicheng Shen, Yue Fan, Cong Zhang, Wangshu Xu, Teng Gu, Jinjie Zheng, Jing Group, Guannan Zhang Ant |
| author_facet | Li, Qiang Yang, Xiaoyan Wang, Haowen Wang, Qin Liu, Lei Wang, Junjie Zhang, Yang Chu, Mingyuan Hu, Sen Chen, Yicheng Shen, Yue Fan, Cong Zhang, Wangshu Xu, Teng Gu, Jinjie Zheng, Jing Group, Guannan Zhang Ant |
| contents | Recently, large language model (LLM) based artificial intelligence (AI) systems have demonstrated remarkable capabilities in natural language understanding and generation. However, these models face a significant challenge when it comes to sensitive applications, such as reasoning over medical knowledge and answering medical questions in a physician-like manner. Prior studies attempted to overcome this challenge by increasing the model size (>100B) to learn more general medical knowledge, while there is still room for improvement in LLMs with smaller-scale model sizes (<100B). In this work, we start from a pre-trained general LLM model (AntGLM-10B) and fine-tune it from a medical beginner towards a medical expert (called AntGLM-Med-10B), which leverages a 3-stage optimization procedure, i.e., general medical knowledge injection, medical domain instruction tuning, and specific medical task adaptation. Our contributions are threefold: (1) We specifically investigate how to adapt a pre-trained general LLM in medical domain, especially for a specific medical task. (2) We collect and construct large-scale medical datasets for each stage of the optimization process. These datasets encompass various data types and tasks, such as question-answering, medical reasoning, multi-choice questions, and medical conversations. (3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs. Remarkably, by combining the above approaches, our AntGLM-Med-10B model can outperform the most of LLMs on PubMedQA, including both general and medical LLMs, even when these LLMs have larger model size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01040 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | From Beginner to Expert: Modeling Medical Knowledge into General LLMs Li, Qiang Yang, Xiaoyan Wang, Haowen Wang, Qin Liu, Lei Wang, Junjie Zhang, Yang Chu, Mingyuan Hu, Sen Chen, Yicheng Shen, Yue Fan, Cong Zhang, Wangshu Xu, Teng Gu, Jinjie Zheng, Jing Group, Guannan Zhang Ant Computation and Language Recently, large language model (LLM) based artificial intelligence (AI) systems have demonstrated remarkable capabilities in natural language understanding and generation. However, these models face a significant challenge when it comes to sensitive applications, such as reasoning over medical knowledge and answering medical questions in a physician-like manner. Prior studies attempted to overcome this challenge by increasing the model size (>100B) to learn more general medical knowledge, while there is still room for improvement in LLMs with smaller-scale model sizes (<100B). In this work, we start from a pre-trained general LLM model (AntGLM-10B) and fine-tune it from a medical beginner towards a medical expert (called AntGLM-Med-10B), which leverages a 3-stage optimization procedure, i.e., general medical knowledge injection, medical domain instruction tuning, and specific medical task adaptation. Our contributions are threefold: (1) We specifically investigate how to adapt a pre-trained general LLM in medical domain, especially for a specific medical task. (2) We collect and construct large-scale medical datasets for each stage of the optimization process. These datasets encompass various data types and tasks, such as question-answering, medical reasoning, multi-choice questions, and medical conversations. (3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs. Remarkably, by combining the above approaches, our AntGLM-Med-10B model can outperform the most of LLMs on PubMedQA, including both general and medical LLMs, even when these LLMs have larger model size. |
| title | From Beginner to Expert: Modeling Medical Knowledge into General LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2312.01040 |