Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917696562528256 |
|---|---|
| author | Zhao, Lulu Zeng, Weihao Shi, Xiaofeng Zhou, Hua Hao, Donglin Lin, Yonghua |
| author_facet | Zhao, Lulu Zeng, Weihao Shi, Xiaofeng Zhou, Hua Hao, Donglin Lin, Yonghua |
| contents | Recently, both closed-source LLMs and open-source communities have made significant strides, outperforming humans in various general domains. However, their performance in specific professional fields such as medicine, especially within the open-source community, remains suboptimal due to the complexity of medical knowledge. We propose Aquila-Med, a bilingual medical LLM based on Aquila, addressing these challenges through continue pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). We construct a large-scale Chinese and English medical dataset for continue pre-training and a high-quality SFT dataset, covering extensive medical specialties. Additionally, we develop a high-quality Direct Preference Optimization (DPO) dataset for further alignment. Aquila-Med achieves notable results across single-turn, multi-turn dialogues, and medical multiple-choice questions, demonstrating the effectiveness of our approach. We open-source the datasets and the entire training process, contributing valuable resources to the research community. Our models and datasets will released at https://huggingface.co/BAAI/AquilaMed-RL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12182 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models Zhao, Lulu Zeng, Weihao Shi, Xiaofeng Zhou, Hua Hao, Donglin Lin, Yonghua Computation and Language Artificial Intelligence Recently, both closed-source LLMs and open-source communities have made significant strides, outperforming humans in various general domains. However, their performance in specific professional fields such as medicine, especially within the open-source community, remains suboptimal due to the complexity of medical knowledge. We propose Aquila-Med, a bilingual medical LLM based on Aquila, addressing these challenges through continue pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). We construct a large-scale Chinese and English medical dataset for continue pre-training and a high-quality SFT dataset, covering extensive medical specialties. Additionally, we develop a high-quality Direct Preference Optimization (DPO) dataset for further alignment. Aquila-Med achieves notable results across single-turn, multi-turn dialogues, and medical multiple-choice questions, demonstrating the effectiveness of our approach. We open-source the datasets and the entire training process, contributing valuable resources to the research community. Our models and datasets will released at https://huggingface.co/BAAI/AquilaMed-RL. |
| title | Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.12182 |