Andrei Stefan Bejgu

NLP Researcher @ Babelscape | Ph.D. in Artificial Intelligence @ Sapienza University of Rome

prof_pic.png

Hi, I’m Andrei Stefan Bejgu, an NLP Researcher at Babelscape based in Rome. I transform state-of-the-art insights into robust AI solutions by developing retrieval-augmented systems and fine-tuning multilingual LLMs using scalable, distributed training methods. My work bridges the gap between research and production, turning complex NLP challenges into high-performance, production-grade products.

I earned my industrial Ph.D. at Sapienza University of Rome, where I deepened my expertise in multilingual NLP and advanced machine learning techniques—an experience that continues to shape my approach to real-world innovations.

With a background spanning software development, engineering, and advanced research, I thrive on collaborating with multidisciplinary teams and mentoring emerging talent throughout every stage of a project. When I’m not immersed in code or research, you can find me exploring new ideas in AI and sharing my journey on social media.

Feel free to connect with me on LinkedIn or drop me an email—I’m always open to exciting collaborations and discussions.

Full CV available here.

selected publications

  1. ArXiv
    Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS
    Alessandro Scirè*, Andrei Stefan Bejgu*, Simone Tedeschi, and 3 more authors
    In Under Review, 2025
    arXiv Bib Code
  2. ACL
    Word Sense Linking: Disambiguating Outside the Sandbox
    Andrei Stefan Bejgu, Edoardo Barba, Luigi Procopio, and 2 more authors
    In ACL, 2024
    Bib Code
  3. EACL
    CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts
    Francesco Molfese, Andrei Stefan Bejgu, Simone Tedeschi, and 2 more authors
    In EACL, 2024
    Bib Code