Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback
This work addresses the need for more consistent and accurate medical dialogue generation, particularly for multi-round conversations, which is an incremental improvement over existing methods.
The paper tackles the problem of logical inconsistencies in multi-round medical conversations by integrating physician diagnostic logic into large language models using preference learning from process feedback (PLPF), resulting in a 17.6% improvement in diagnostic accuracy over the baseline model.
The use of large language models in medical dialogue generation has garnered significant attention, with a focus on improving response quality and fluency. While previous studies have made progress in optimizing model performance for single-round medical Q&A tasks, there is a need to enhance the model's capability for multi-round conversations to avoid logical inconsistencies. To address this, we propose an approach called preference learning from process feedback~(PLPF), which integrates the doctor's diagnostic logic into LLMs. PLPF involves rule modeling, preference data generation, and preference alignment to train the model to adhere to the diagnostic process. Experimental results using Standardized Patient Testing show that PLPF enhances the diagnostic accuracy of the baseline model in medical conversations by 17.6%, outperforming traditional reinforcement learning from human feedback. Additionally, PLPF demonstrates effectiveness in both multi-round and single-round dialogue tasks, showcasing its potential for improving medical dialogue generation.