Ivan Habernal

Ivan Habernal

ivan.habernal@uni-paderborn.de
Institution: Paderborn University
Department: Department of Computer Science
Position: Head of the Natural Language Processing Group
https://www.trusthlt.org/
We focus on trustworthy human language technologies.

Privacy-preserving natural language processing, legal natural language processing, trustworthy models

  • Private Synthetic Text Generation with Diffusion Models (2025)

    Authors: Sebastian Ochs, Ivan Habernal

    Published at: Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics Human Language Technologies Long Papers Naacl Hlt 2025 (Volume: 1)
    DOI: 10.18653/v1/2025.naacl-long.532

  • The Impact of Inference Acceleration on Bias of LLMs (2025)

    Authors: Elisabeth Kirsten, Ivan Habernal, Vedant Nanda, Muhammad Bilal Zafar

    Published at: Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics Human Language Technologies Long Papers Naacl Hlt 2025 (Volume: 1)
    DOI: 10.18653/v1/2025.naacl-long.91

  • Mining legal arguments in court decisions (2024)

    Authors: Ivan Habernal, Daniel Faber, Nicola Recchia, Sebastian Bretthauer, Iryna Gurevych, Indra Spiecker genannt Döhmann, Christoph Burchard

    Published at: Artificial Intelligence and Law (Volume: 32)
    DOI: 10.1007/s10506-023-09361-y

  • LaCour!: enabling research on argumentation in hearings of the European Court of Human Rights (2024)

    Authors: Lena Held, Ivan Habernal

    Published at: Artificial Intelligence and Law
    DOI: 10.1007/s10506-024-09428-4

  • Answering legal questions from laymen in German civil law system (2024)

    Authors: Marius Büttner, Ivan Habernal

    Published at: Eacl 2024 18th Conference of the European Chapter of the Association for Computational Linguistics Proceedings of the Conference (Volume: 1)

  • SemEval-2024 Task 5: Argument Reasoning in Civil Procedure (2024)

    Authors: Lena Held, Ivan Habernal

    Published at: Semeval 2024 18th International Workshop on Semantic Evaluation Proceedings of the Workshop
    DOI: 10.18653/v1/2024.semeval-1.276

  • To Share or Not to Share: What Risks Would Laypeople Accept to Give Sensitive Data to Differentially-Private NLP Systems? (2024)

    Authors: Christopher Weiss, Frauke Kreuter, Ivan Habernal

    Published at: 2024 Joint International Conference on Computational Linguistics Language Resources and Evaluation Lrec Coling 2024 Main Conference Proceedings

  • Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation (2024)

    Authors: Doan Nam Long Vu, Timour Igamberdiev, Ivan Habernal

    Published at: Emnlp 2024 2024 Conference on Empirical Methods in Natural Language Processing Findings of Emnlp 2024
    DOI: 10.18653/v1/2024.findings-emnlp.29

  • Differentially Private Natural Language Models: Recent Advances and Future Directions (2024)

    Authors: Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

    Published at: Eacl 2024 18th Conference of the European Chapter of the Association for Computational Linguistics Findings of Eacl 2024

  • Private Language Models via Truncated Laplacian Mechanism (2024)

    Authors: Tianhao Huang, Tao Yang, Ivan Habernal, Lijie Hu, Di Wang

    Published at: Emnlp 2024 2024 Conference on Empirical Methods in Natural Language Processing Proceedings of the Conference
    DOI: 10.18653/v1/2024.emnlp-main.231