Babelscape co-founder, Roberto Navigli appointed General Chair of ACL 2025
We are proud to announce that Roberto Navigli, internationally renowned AI professor at Sapienza University and creator of Minerva - Italy's national Large Language Model - will serve as General Chair of ACL 2025, the world's premier conference on Natural Language Processing.
Held in Vienna from July 27 to August 1, ACL 2025 is set to be the largest edition in the conference's history, with nearly 6,000 participants from academia, industry, and major global tech players.
Graph RAG: smarter AI retrieval through knowledge graphs
Retrieval-Augmented Generation (RAG) has revolutionized how AI systems access information, but it still struggles with context limitations and factual hallucinations.
At Babelscape, we have been experimenting with this technology on our multilingual knowledge graph WordAtlas (and others!) for quite some time now, with the aim of demonstrating how Graph RAG can transform AI understanding across languages.
La Repubblica Talks About Us!
From Research Comes AI: All Made in Italy.
We had a conversation with La Repubblica about our commitment to creating synergy between the academic and industrial worlds.
It is from this synergy that innovative tools like Babelscape Vera emerge—a fact-checking system that we are proud to present at Maker Faire, bridging cutting-edge research with real-world applications.
Babelscape Vera is now live - Try the free demo!
We’re thrilled to announce that Babelscape Vera, our LLM-powered virtual assistant for fact-checking, is now online!
Vera intelligently gathers, analyzes, and validates claims using credible sources, ensuring accuracy and transparency
through in-depth, evidence-based analysis.
The live demo is now available, try it for free and experience the future of fact-checking today!
“Babelscape Vera: LLM-powered Fact-Checking” to Be Presented at Maker Faire 2024!
We are excited to introduce Vera, our LLM-powered fact-checking tool, at Maker Faire 2024 in Rome from October 25-27. Vera automates claim verification by retrieving, analyzing, and classifying information as true, false, neutral, or controversial using trusted sources, whether from the Web or proprietary knowledge bases.
Join us at Maker Faire Rome for a live demo of Vera!
Minerva: Italy's First Family of Large Language Models trained on Italian texts
The Minerva family of large language models (LLMs) is reshaping the AI landscape in Italy. Created by Sapienza NLP in collaboration with FAIR (Future Artificial Intelligence Research) and CINECA, with additional support from Babelscape, Minerva is the first suite of AI models built from scratch to serve Italian-language needs while also supporting English.
”NounAtlas: Filling the Gap in Nominal Semantic Role Labeling” has been awarded as Outstanding paper!
We are excited to announce that our work “NounAtlas: Filling the Gap in Nominal Semantic Role Labeling” has been awarded as
Outstanding paper at ACL 2024!
Many congratulations to the authors Roberto Navigli, Marco Lo Pinto, Pasquale Silvestri, Dennis Rotondi,
Simone Ciciliano and Alessandro Scirè.