Abstract background shapeAbstract background shape

Large Language Models

Harness the power of AI for language understanding

Leverage the potential of artificial intelligence with our state-of-the-art Large Language Models. Designed to understand and generate human-like text, our LLMs provide a foundation for numerous applications, from conversational AI to deep content analysis. These models are trained on extensive datasets to ensure nuanced understanding and generation capabilities across various languages and contexts.

Large Language Models header logo
Header shape illustration 2

Minerva

The First Italian LLM

In collaboration with Babelscape, Minerva is being transformed into a robust, production-ready solution for businesses. Babelscape is leading the industrialization of the model, tailoring it for real-world applications in public administration, healthcare, culture, education, and more. Minerva is already being tested to analyze legal texts and understand clinical documents, opening the door to highly specialized use cases across various industries.

What's next for Minerva

The team is already developing Minerva Version 2, which will feature:

  • Larger model
  • Long-context understanding
  • Verticalization by domain
  • Built-in reasoning and commonsense mechanisms

Our mission: create a reliable, industrially viable "zero-mile" Italian model that ensures Italy's technological independence, from PA to the industry.

Minerva AI: chatbot preview

Agentic AI to solve real problems

Deploy intelligent AI agents designed to tackle real-world challenges across industries. Our agentic AI solutions leverage both open-source and proprietary language models to create autonomous systems that can reason, plan, and execute complex tasks with minimal human intervention.


Contact us to discuss your specific use case and discover how agentic AI can transform your operations.

Agentic AI to solve real problems representation

Retrieval-Augmented Generation (RAG)

Combine the expressive power of LLMs with external knowledge sources using Retrieval-Augmented Generation. This approach integrates real-time data retrieval at the semantic level with generative capabilities, enabling the model to access and incorporate the latest, most relevant information while generating text.


Our RAG implementations support diverse data architectures including traditional SQL databases, graph databases like Neo4j, vector stores, and hybrid document repositories — ensuring your AI solutions are accurate, contextually relevant, and optimized for your specific data infrastructure.

Retrieval-Augmented Generation (RAG) representation

Custom model training and fine-tuning

Tailor LLMs to your specific needs by training them on your proprietary datasets, ensuring they align perfectly with your business context and requirements. Customization allows for greater precision and relevancy in responses, optimizing AI performance to better serve your strategic objectives.


Leveraging our deep research background and continuous collaboration with the internationally acclaimed Sapienza NLP research group, we excel at personalizing language models for highly specific use cases, from domain adaptation to multilingual fine-tuning.

Custom model training and fine-tuning representation

AI evaluation for reliable outcomes

Ensure your AI systems perform with accuracy, consistency, and accountability. Our evaluation framework combines automated metrics with human-in-the-loop review to assess language models across relevance, factual grounding, coherence, and alignment with task objectives.


Drawing from our extensive research heritage and ongoing exchange with Sapienza NLP, we bring world-class expertise in model evaluation and custom benchmark creation, ensuring your AI delivers trustworthy, high-performance results tailored to your domain and use case.

AI evaluation for reliable outcomes representation

Use Cases

Our Large Language Models are at the heart of transformative solutions across various sectors. By understanding and generating human-like text, these models enable organizations to enhance communication, automate content creation, and extract insights from vast amounts of data.

Discover how different industries leverage our LLMs to innovate and improve efficiency, accuracy, and engagement.

Contact us

Customer service

Enhance customer interaction with AI-driven support that understands and resolves queries efficiently, improving satisfaction and engagement.

Marketing and advertising

Create compelling, targeted content automatically and scale communication strategies to reach diverse audiences with personalized messaging.

Financial services

Analyze large volumes of financial documents quickly, extract key information, and generate reports, enhancing decision-making processes.

Healthcare

Support medical professionals by summarizing patient information, generating medical documentation, and providing insights from clinical data.

Related products

Contacts

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Message sent successfully logo
Message sent successfully

Your message has been sent correctly.
Thank you for reaching out to us. We will get back to you as soon as possible.

Message sent successfully logo
Something went wrong

We are sorry, your request cannot be processed right now.
Please wait a bit and try again.

Your privacy choices

Save and continue
Sign up!
The best way to get the latest news from Babelscape and the NLP world!
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Thank you for subscribing!
You’ve been added to our mailing list, and you’ll receive our next newsletter to stay updated on the latest news from the NLP world!
Something went wrong
We are sorry, your request cannot be processed right now.
Please wait a bit and try again.
Unsubscribe
We're sorry to see you go. Please enter your email address to complete the unsubscription process.
You'll receive an email confirmation shortly.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Check your email
We have sent you a link to your email to complete the unsubscribe process.
Something went wrong
We are sorry, your request cannot be processed right now.
Please wait a bit and try again.