UltraMedical: Building Specialized Generalists in Biomedicine

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Kaiyan, Zeng, Sihang, Hua, Ermo, Ding, Ning, Chen, Zhang-Ren, Ma, Zhiyuan, Li, Haoxin, Cui, Ganqu, Qi, Biqing, Zhu, Xuekai, Lv, Xingtai, Jinfang, Hu, Liu, Zhiyuan, Zhou, Bowen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929566046486528
author Zhang, Kaiyan
Zeng, Sihang
Hua, Ermo
Ding, Ning
Chen, Zhang-Ren
Ma, Zhiyuan
Li, Haoxin
Cui, Ganqu
Qi, Biqing
Zhu, Xuekai
Lv, Xingtai
Jinfang, Hu
Liu, Zhiyuan
Zhou, Bowen
author_facet Zhang, Kaiyan
Zeng, Sihang
Hua, Ermo
Ding, Ning
Chen, Zhang-Ren
Ma, Zhiyuan
Li, Haoxin
Cui, Ganqu
Qi, Biqing
Zhu, Xuekai
Lv, Xingtai
Jinfang, Hu
Liu, Zhiyuan
Zhou, Bowen
contents Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements in biomedicine, which have also raised privacy and security challenges. The construction of specialized generalists hinges largely on high-quality datasets, enhanced by techniques like supervised fine-tuning and reinforcement learning from human or AI feedback, and direct preference optimization. However, these leading technologies (e.g., preference learning) are still significantly limited in the open source community due to the scarcity of specialized data. In this paper, we present the UltraMedical collections, which consist of high-quality manual and synthetic datasets in the biomedicine domain, featuring preference annotations across multiple advanced LLMs. By utilizing these datasets, we fine-tune a suite of specialized medical models based on Llama-3 series, demonstrating breathtaking capabilities across various medical benchmarks. Moreover, we develop powerful reward models skilled in biomedical and general reward benchmark, enhancing further online preference learning within the biomedical LLM community. Datasets and models are available at https://github.com/TsinghuaC3I/UltraMedical
format Preprint
id arxiv_https___arxiv_org_abs_2406_03949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UltraMedical: Building Specialized Generalists in Biomedicine
Zhang, Kaiyan
Zeng, Sihang
Hua, Ermo
Ding, Ning
Chen, Zhang-Ren
Ma, Zhiyuan
Li, Haoxin
Cui, Ganqu
Qi, Biqing
Zhu, Xuekai
Lv, Xingtai
Jinfang, Hu
Liu, Zhiyuan
Zhou, Bowen
Computation and Language
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements in biomedicine, which have also raised privacy and security challenges. The construction of specialized generalists hinges largely on high-quality datasets, enhanced by techniques like supervised fine-tuning and reinforcement learning from human or AI feedback, and direct preference optimization. However, these leading technologies (e.g., preference learning) are still significantly limited in the open source community due to the scarcity of specialized data. In this paper, we present the UltraMedical collections, which consist of high-quality manual and synthetic datasets in the biomedicine domain, featuring preference annotations across multiple advanced LLMs. By utilizing these datasets, we fine-tune a suite of specialized medical models based on Llama-3 series, demonstrating breathtaking capabilities across various medical benchmarks. Moreover, we develop powerful reward models skilled in biomedical and general reward benchmark, enhancing further online preference learning within the biomedical LLM community. Datasets and models are available at https://github.com/TsinghuaC3I/UltraMedical
title UltraMedical: Building Specialized Generalists in Biomedicine
topic Computation and Language
url https://arxiv.org/abs/2406.03949