English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent advances in Large Language Models (LLMs) have achieved remarkablebreakthroughs in understanding and responding to user intents. However, theirperformance lag behind general use cases in some expertise domains, such asChinese medicine. Existing efforts to incorporate Chinese medicine into LLMsrely on Supervised Fine-Tuning (SFT) with single-turn and distilled dialoguedata. These models lack the ability for doctor-like proactive inquiry andmulti-turn comprehension and cannot align responses with experts' intentions.In this work, we introduce Zhongjing, the first Chinese medical LLaMA-based LLMthat implements an entire training pipeline from continuous pre-training, SFT,to Reinforcement Learning from Human Feedback (RLHF). Additionally, weconstruct a Chinese multi-turn medical dialogue dataset of 70,000 authenticdoctor-patient dialogues, CMtMedQA, which significantly enhances the model'scapability for complex dialogue and proactive inquiry initiation. We alsodefine a refined annotation rule and evaluation criteria given the uniquecharacteristics of the biomedical domain. Extensive experimental results showthat Zhongjing outperforms baselines in various capacities and matches theperformance of ChatGPT in some abilities, despite the 100x parameters. Ablationstudies also demonstrate the contributions of each component: pre-trainingenhances medical knowledge, and RLHF further improves instruction-followingability and safety. Our code, datasets, and models are available athttps://github.com/SupritYoung/Zhongjing.

Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue