Fully Open Meditron: An Auditable Pipeline for Clinical LLMs
Research paper by Xavier Theimer-Lienhard and collaborators. arXiv record dated 2026-05-29. Research area: Artificial intelligence.
5,427,056 AI resources indexedWorking toward the world’s largest AI resource index.
Publications about AI methods and applications.
Research paper by Xavier Theimer-Lienhard and collaborators. arXiv record dated 2026-05-29. Research area: Artificial intelligence.
Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source (e.g., PaLM, GPT-4) or limited in scale (<= 13B parameters), which restricts their abilities. In this work, we improve access to large-scale medical LLMs by releasing MEDITRON: a suite of open-source LLMs with 7B and 70B parameters adapted to the medical domain. MEDITRON builds on Llama-2 (through our adaptation of Nvidia's Megatron-LM distributed trainer), and extends pretraining on a comprehensively curate
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.