Enhancing Dynamic Personalization in Dietitian Agents with RAG and Medical Dialogue Fine-Tuning

We present an AI dietitian chatbot that generates factually accurate and empathetic responses. The system employs an agentic AI architecture and incorporates a nutrition database and two Large Language Models (LLMs), one of which is fine-tuned with natural doctor-patient conversations. A preliminary evaluation is performed using an LLM-as-a-judge approach, where the system’s responses are evaluated against a baseline model with regard to factual consistency and empathy. Preliminary results show much improved retrieval consistency and empathy in our responses compared to the baseline model.