BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains
Laboratoire Informatique d'Avignon · Laboratoire des Sciences du Numérique de Nantes · +2 more institutions
Abstract
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…
Citation impact
- FWCI
- 61.52
- Percentile
- 100%
- References
- 0
Authors
6- YLYanis LabrakCorresponding
Laboratoire Informatique d'Avignon
- ABAdrien Bazoge
Laboratoire des Sciences du Numérique de Nantes, Nantes Université
- EMEmmanuel Morin
Laboratoire des Sciences du Numérique de Nantes, Nantes Université
- PGPierre‐antoine Gourraud
Centre d'Investigation Clinique de Nantes
- MRMickaël Rouvier
Laboratoire Informatique d'Avignon
Topics & keywords
- Computer science
- Scripting language
- Benchmark (surveying)
- Open source
- Domain-specific language
- Domain (mathematical analysis)
- Data science
- Language model
- Quality Education