In the past few years, ChatGPT has been grabbing all the headlines and attention worldwide. But there are other language models that are undoubtedly revolutionizing all kinds of industries, such as Life Sciences. That is why many companies, like Narrativa, are investing in creating the best technology for the advancement of science. What is BioGPT, Microsoft’s language model for Life Sciences?

BioGPT, a model that exceeds human capacity

BioGPT is a language model transformer that has been developed by Microsoft researchers. Its primary function is to answer biomedical questions, and according to the American company, BioGPT even exceeds the knowledge level of human experts.

These types of models accelerate medical research for treatments and drugs, so their reliability is essential. It has two main uses:

• Question answering
• Entity extraction

As you know, Narrativa develops solutions for the pharmaceutical sector so that approvals and introductions to the marketplace occur more quickly. We have tested this model and find the combination of Narrativa and Microsoft technology to be incredible.

How has BioGPT been trained?

Microsoft Research created and trained this model exclusively for the biomedical field. Specifically, biomedical papers, including 15 million PubMed abstracts, were used.

The fine tuning of the model also surpasses other models created globally, such as GPT-3 and FLAN, reaching 81% accuracy. The next closest model reached 79 percent.

An impressive fact is that among all versions of BioGPT, the most powerful has 1.5 billion parameters.

When it comes to training models, more is not always better

Why is BioGPT such a strong model at a technological level? Simply put, the model has been trained with very specific texts, which makes its knowledge base highly precise.

If we were going to train a model to know everything about cars, for instance, it would make sense to feed it millions of pieces of information specifically about cars. The same principle applies here. The more tailored and focused the source data, the better the output. As the saying goes, garbage in, garbage out.

Can I try it out myself?

Yes. Microsoft has released the model, though only for certain tasks. Check it out here.

Language models like BioGPT demonstrate how AI can analyze biomedical information at scale. However, turning clinical data into regulatory ready documentation requires specialized technologies designed for pharmaceutical workflows. This is where AI platforms such as Narrativa help organizations transform complex clinical data into structured regulatory documentation.

In 2025, Narrativa generated more than 65,000 regulatory compliance documents for pharmaceutical companies across multiple markets.

Accelerating drug creation

Despite the growing use of AI in healthcare, there are still areas where its potential is underrepresented. Regulatory submission is one such area. Regulatory submissions, such as clinical study reports, are based on information collected before, during, and after clinical trials.

This data may come from many sources, including thousands of subjects across multiple regions and continents. Someone must review the data, organize it, and transform it into documentation that can be evaluated and approved.

Regulatory submissions automation

Patient safety narratives automation

Patient safety narratives are a key part of clinical study reporting. Automating patient safety reports can help save time by handling repetitive elements.

Automating tables, listings, and figures

Narrativa’s TLF automation solution analyzes and summarizes datasets from clinical studies and transforms them into ready to use Tables, Listings, and Figures.

Automation of clinical study reports (CSRs)

Narrativa Knowledge Graph® and deep learning language algorithms automate the generation of clinical study reports through data extraction and augmentation.

2025 key results for our clients.

As AI continues to evolve, specialized language models such as BioGPT are expected to play a growing role in biomedical research and drug development. Combined with platforms that automate clinical documentation and regulatory reporting, these technologies have the potential to significantly accelerate scientific discovery and improve efficiency across the life sciences industry.