Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks

arXiv:2404.00376v1 Announce Type: new
Abstract: While recent advancements in commercial large language models (LM) have shown promising results in medical tasks, their closed-source nature poses significant privacy and security concerns, hindering their widespread use in the medical field. Despite efforts to create open-source models, their limited parameters often result in insufficient multi-step reasoning capabilities required for solving complex medical problems. To address this, we introduce Meerkat-7B, a novel medical AI system with 7 billion parameters. Meerkat-7B was trained using our …

abstract arxiv commercial concerns cs.cl language language models large language large language models learn medical medical field nature open-source models parameters privacy privacy and security reasoning results security security concerns skills small small language models tasks type