Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models

arXiv:2401.15269v2 Announce Type: replace
Abstract: Recent proprietary large language models (LLMs), such as GPT-4, have achieved a milestone in tackling diverse challenges in the biomedical domain, ranging from multiple-choice questions to long-form generations. To address challenges that still cannot be handled with the encoded knowledge of LLMs, various retrieval-augmented generation (RAG) methods have been developed by searching documents from the knowledge corpus and appending them unconditionally or selectively to the input of LLMs for generation. However, when applying existing methods …

abstract arxiv biomedical challenges cs.ai cs.cl cs.ir diverse domain form gpt gpt-4 improving knowledge language language models large language large language models llms medical multiple proprietary questions reasoning retrieval retrieval-augmented through type