LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination

arXiv:2309.11696v3 Announce Type: replace
Abstract: Large Language Models (LLMs), such as GPT3.5, have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, medical assistants hold the potential to offer substantial benefits for individuals. However, the exploration of LLM-based personalized medical assistant remains relatively scarce. Typically, patients converse differently based on their background and preferences which necessitates the task of enhancing user-oriented medical assistant. While one can fully train an LLM for this objective, the resource consumption …

abstract arxiv assistant assistants benefits cs.cl exploration gpt3 gpt3.5 however language language models large language large language models llm llms long-term medical memory natural natural language patients personalization personalized type