Belgian AI company builds groundbreaking new language model that detects online hate speech in all European languages
World's first multilingual hate speech detector
Antwerp - Textgain takes another major step forward in the fight against hate speech and disinformation on the internet. The University of Antwerp’s AI spin-off won a prestigious competition for European AI developers in June. It is now building a robust AI tool from the ground up. This tool will detect online hate speech in all official European languages.
Textgain is building CaLICO over the next twelve months; it will be the world's first advanced Large Language Model (LLM) that recognizes and processes hate speech in all official EU languages. The company aims to become the market leader in multilingual AI-based hate speech detection over the long term.
CEO Guy De Pauw: "Large language models, especially commercial ones, refuse to process toxic language. This makes it almost impossible to use them to process hate speech. We are now building a language model from scratch that can process this type of content — but without generating it. That's what makes us different."
Winner of European AI competition
Textgain recently received a strong boost as one of the four winners of the Large AI Grand Challenge, a prestigious competition for European AI developers in which 94 international companies participated. It won not only €250,000, but also two million hours of development time on a European supercomputer allowing for much faster new AI model training.
COO Redouan el Hamouchi: "In our digitalized world, there is a growing need for advanced tools to moderate content. Multilingualism is essential in this respect. We are pleased that we can train our application faster, so that it can handle different languages and cultures within the European Union."
International expansion
Textgain has great ambitions. The coming year will focus on the development of the AI 'Hate Speech' model, with a nominal value of several million euros. With a view towards international expansion, the company will then focus – from a vantage point as market leader – on the further development of SaaS applications.
"We have a unique position in the saturated market of AI providers," says De Pauw: "Firstly, because we are developing our own language model, instead of building on existing AI models. This immediately positions us alongside major players such as OpenAI, Google, and Meta. We also distinguish ourselves through our academic approach. We work together with policymakers, security services, social organizations and scientists. Reliability and precision are important rather than generic solutions and unrealistic promises."
Responsible and ethical
Textgain remains committed to mapping social problems using AI technology. "The European Union has set strict standards," says De Pauw. "The technology must be transparent, explainable, and ethical. These values are also in our DNA. It’s the only way to give people confidence in new technology."
el Hamouchi confirms: "Our strong ambition also reminds us of our enormous responsibility. That is why we do everything we can to ensure that we meet the highest ethical standards. We are building and will maintain very strict processes to protect privacy."
Textgain is an AI spin-off of the University of Antwerp. The company originated from the university’s Computational Linguistics & Psycholinguistics (CLiPS) Research Center, where innovative research techniques in the field of NLP are developed. Textgain focuses on applying these technologies to address societal challenges, such as detecting hate speech, disinformation, and violent extremism. Textgain is located in Antwerp, Belgium
kevin major
saar dietvorst