Med42-v2: A Suite of Clinical LLMs
This addresses the need for reliable AI assistance in clinical environments, though it is incremental as it builds on existing architectures with domain-specific tuning.
The paper tackles the problem of generic large language models being limited in healthcare settings by introducing Med42-v2, a suite of clinical LLMs fine-tuned on specialized data, which demonstrates superior performance over Llama3 and GPT-4 on medical benchmarks.
Med42-v2 introduces a suite of clinical large language models (LLMs) designed to address the limitations of generic models in healthcare settings. These models are built on Llama3 architecture and fine-tuned using specialized clinical data. They underwent multi-stage preference alignment to effectively respond to natural prompts. While generic models are often preference-aligned to avoid answering clinical queries as a precaution, Med42-v2 is specifically trained to overcome this limitation, enabling its use in clinical settings. Med42-v2 models demonstrate superior performance compared to the original Llama3 models in both 8B and 70B parameter configurations and GPT-4 across various medical benchmarks. These LLMs are developed to understand clinical queries, perform reasoning tasks, and provide valuable assistance in clinical environments. The models are now publicly available at \href{https://huggingface.co/m42-health}{https://huggingface.co/m42-health}.