DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
This work addresses the need for reliable AI in medical consultation, though it appears incremental as it builds on existing LLM methods with domain-specific adaptations.
The authors tackled the problem of providing accurate medical responses in conversational healthcare by developing DISC-MedLLM, which surpassed existing medical LLMs in single-turn and multi-turn consultation scenarios.
We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonstrate the effectiveness of the proposed model in bridging the gap between general language models and real-world medical consultation. Additionally, we release the constructed dataset and model weights to further contribute to research and development. Further details and resources can be found at https://github.com/FudanDISC/DISC-MedLLM