BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains
By Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, Richard Dufour. Annual Meeting of the Association for Computational Linguistics, 2024
514 citations recorded by the source corpus.
Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released.
View Paper: https://www.semanticscholar.org/paper/13b8934468665ecb586f491d7f9f6c460cb095e5
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Kai He
- Qika Lin
- Xiang Lan
- Rui Mao
- Qing-Qing Long
- Mengling Feng
- Yucheng Ruan
- Xunxin Cai
Citations in the corpus
- A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, background): “This instability is more matters for Healthcare than other general applications.”
- Effects of Model Choice, Corpus Context, and Post Hoc Correction on Layer-Level Embedding Degradation in Clinical Document Retrieval: Experimental Study (2026, unknown): “…[4], ClinicalBERT [5]), general encoders (BERT-base-uncased [28]), biomedical retrievers (BioLORD-2023 [13], MedCPT [29]), general-purpose retrievers (BGE-base [6], GTE-base [7], Nomic-embed-text [8]), general LLMs (E5-Mistral-7B [30], Phi-3-mini [31]), and biomedical LLMs (BioMistral-7B [32]).”
- “Small” Large Language Models in the Hospital: Evaluation Study on Real-World Data in a Resource-Constrained Setting (2025, unknown): “For instance, models such as BioGPT [14] and BioMistral-7B [15] were not considered due to their limited context window, while others (eg, MedLM [16]) were excluded due to the lack of publicly available model weights, preventing reproducible evaluation.”
- BioRAG: A RAG-LLM Framework for Biological Question Reasoning (2024, background): “• BioLLM (Biological LLMs): PMC-Llama (13B) (Wu et al., 2024) and BioMistral (7B) (Labrak et al., 2024) are two medical LLMs.”