HuatuoGPT, towards Taming Language Model to Be a Doctor

By Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu, Zhihong Chen, Jianquan Li, Guimin Chen, Xiangbo Wu, Zhiyi Zhang, Qingying Xiao and 3 more. Conference on Empirical Methods in Natural Language Processing, 2023

371 citations recorded by the source corpus.

In this paper, we present HuatuoGPT, a large language model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both \textit{distilled data from ChatGPT} and \textit{real-world data from doctors} in the supervised fine-tuned stage. The responses of ChatGPT are usually detailed, well-presented and informative while it cannot perform like a doctor in many aspects, e.g. for integrative diagnosis. We argue that real-world data from doctors would be complementary to distilled data in the sense the former could tame a distilled language model to perform like doctors. To better leverage the strengths of both data, we train a reward model to align the language model with the merits that both data bring, following an RLAIF (reinforced learning from AI feedback) fashion. To evaluate and benchmark the models, we propose a comprehensive evaluation scheme (including automatic and manual metrics). Experimental results demonstrate that HuatuoGPT achieves state-of-the-art results in performing medical consultation among open-source LLMs in GPT-4 evaluation, human evaluation, and medical benchmark datasets. It is worth noting that by using additional real-world data and RLAIF, the distilled language model (i.e., HuatuoGPT) outperforms its teacher model ChatGPT in most cases. Our code, data, and models are publicly available at \url{https://github.com/FreedomIntelligence/HuatuoGPT}. The online demo is available at \url{https://www.HuatuoGPT.cn/}.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/5459cab5dcf3c65c6b4f63b3d9f1e376f722bbcb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qika Lin
2. Xiang Lan
3. Rui Mao
4. Kai He
5. Mengling Feng
6. Yucheng Ruan
7. Erik Cambria
8. Soujanya Poria

Citations in the corpus

• Recommender Systems in the Era of Large Language Models (LLMs) (2023, neutral): “More recently, existing works have presented vertical domain-specific LLMs that cover a wide range of areas, such as medical care [116], [117], law [118], [119], and finance [120].”
• A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, positive): “These advanced improvements present a remarkable opportunity for LLMs to contribute significantly to Healthcare, such as the released LLMs of HuatuoGPT [44], Med-PaLM 2 [16], and Visual Med-Alpaca [45].”