Skip to main content Skip to main navigation

Interim Head of the Research Department Multilinguality and Language Technology

Dr. Simon Ostermann

Address (Saarbrücken) Gebäude D3 2Stuhlsatzenhausweg 366123 Saarbrücken

Publications

All publications
  1. Multilingual Political Views of Large Language Models: Identification and Steering

    Daniil Gurgurov; Katharina Trinley; Ivan Vykopal; Josef van Genabith; Simon Ostermann; Roberto Zamparelli

    In: Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL-2025), December 20-24, Mumbai, India, The Asian Federation of…
  2. On Multilingual Encoder Language Model Compression for Low-Resource Languages

    Daniil Gurgurov; Michal Gregor; Josef van Genabith; Simon Ostermann

    In: Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL-2025), December 20-24, Mumbai, India, The Asian Federation of…

Profile

  • soofi

    Sovereign Open Source Foundation Models

    We are developing a larger AI language model that will be made available to the economy and society as open source. Based on a large language model (LLM), a so-called reasoning model will also be…

    soofi
  • lorAI

    Low Resource Artificial Intelligence

    The main objective of the lorAI project is to upgrade the Kempelen Institute of Intelligent Technologies (KInIT) to a leading R&I institution in low resource artificial intelligence (LRAI) in Slovakia…

    lorAI
  • TRAILS

    Trustworthy and Inclusive Machines

    Natural language processing (NLP) has demonstrated impressive performance in some human tasks. To achieve such performance, current neural models need to be pre-trained on huge amounts of raw text…

    TRAILS
  • PERKS

    Eliciting and Exploiting Procedural Knowledge in Industry 5.0

    The PERKS project supports the holistic governance of industrial PK in its entire life cycle, from elicitation to management and from access to exploitation. PERKS bases its solutions on leading-edge…

    PERKS
  • DAM-S

    Semantische Suche für das "Meere Online"-Portal der Deutschen Allianz Meeresforschung

    Entwicklung einer semantischen, KI-gestützten Suchfunktion für das Portal "Meere Online" für die Deutsche Allianz Meeresforschung (DAM)

     

Show all projects