The TUM Legal Tech Group

The professorship in Legal Tech conducts research and development around the application of methods from artificial intelligence, machine learning, data science, natural language processing, and knowledge engineering towards solving tasks and problems arising in the practice of law and public administration. High level goals are to:

  • Support judicial decision making
  • Facilitate access to justice
  • Enable effective research in collections of legal documents
  • Enhance processes in public administration and legal practice

Currently, specific technical areas of focus include:

  • Natural language processing of legal text, in particular with regard to effectively combining it with legal expertise
  • Information retrieval on legal text
  • Computational models of legal inference and argumentation (i.e. rule- and case-based reasoning)


  • Santosh, T. Y. S.S., Venkatkrishna, V., Ghosh, S., & Grabmair, M. Beyond Borders: Investigating Cross-Jurisdiction Transfer in Legal Case Summarization. (to appear in NACCL 2024) [arxiv]
  • Santosh, T. Y. S.S., Sarwat, H., Abdou, A., & Grabmair, M. Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents. (LREC-COLING 2024) [arxiv]
  • Santosh, T. Y. S.S., Haddad, R. G., & Grabmair, M. ECtHR-PCR: A Dataset for Precedent Understanding and Prior Case Retrieval in the European Court of Human Rights. (LREC-COLING 2024) [arxiv]
  • Santosh, T. Y. S.S., Kaiser, K., & Grabmair, M. CuSINeS: Curriculum-driven Structure Induced Negative Sampling for Statutory Article Retrieval. (LREC-COLING 2024) [arxiv]
  • Santosh, T. Y. S.S., Aly, M., & Grabmair, M. LexAbSumm: Aspect-based Summarization of Legal Decisions. arXiv preprint arXiv:2404.00594. (LREC-COLING 2024) [arxiv]
  • Santosh, T. Y. S.S., Hernandez, E. Q., & Grabmair, M. Query-driven Relevant Paragraph Extraction from Legal Judgments. (LREC-COLING 2024) [arxiv]
  • Santosh, T.Y.S.S., Baumgartner, N., Stürmer, M., Grabmair, M., & Niklaus, J. (2024). Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset. (LREC-COLING 2024) [arxiv]
  • Santosh, T.Y.S.S., Vuong, T. Q., & Grabmair, M. (2024). ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks. (ACL 20204) [arxiv]
  • Xu, S., Santosh, T. Y. S.S., Ichim, O., Plank, B., & Grabmair, M. (2024). Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification. (ACL 2024) [arxiv]
  • Xu, S., Santosh, T.Y.S.S., Ichim, O., Risini, I., Plank, B., & Grabmair, M. (2023). From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification. (EMNLP 2023). [arxiv]
  • Xu, S., Staufer, L., Santosh, T.Y.S.S., Ichim, O., Heri, C., & Grabmair, M. (2023). VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights. (EMNLP 2023). [arxiv]
  • Santosh, T.Y.S.S., Blas M., Kemper, P. and Grabmair, M. Leveraging task dependency and contrastive learning for Legal Judgement Prediction on the European Court of Human Rights. (EACL 2023) [arxiv].
  • Santosh, T.Y.S.S., Ichim O, Grabmair M. Zero Shot Transfer of Legal Judgement Prediction as Article-aware Entailment for the European Court of Human Rights. (Findings of EACL 2023) [arxiv].
  • Santosh, T.Y.S.S., Bock, P. and Grabmair, M.. Joint Span Segmentation and Rhetorical Role Labelling with Data Augmentation for Legal Documents. (ECIR 2023) [arxiv]
  • Schirmer, M., Nolasco, I. M. O., Mosca, E., Xu, S., & Pfeffer, J. Uncovering Trauma in Genocide Tribunals: An NLP Approach Using the Genocide Transcript Corpus. (ICAIL 2023) [pdf]
  • Santosh, T.Y.S.S., Xu, S., Ichim, O. and Grabmair, M., 2022. Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) [arxiv].
  • Agarwal, A., Xu, S. and Grabmair, M., 2022. Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance, Findings of the 2022 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2022) [arxiv].
  • Xu, S., Broda, I., Haddad, R., Negrini, M. and Grabmair, M., 2022. Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers. Proceedings of the 2022 Workshop on Natural Legal Language Processing (NLLP 2022) [arxiv].
  • Governatori, G., Bench-Capon, T., Verheij, B., Araszkiewicz, M., Francesconi, E. and Grabmair, M., 2022. Thirty years of Artificial Intelligence and Law: the first decade. Artificial Intelligence and Law, pp.1-39 [pdf].
  • Z. Huang, C. Low, M. Teng, H. Zhang, D. E. Ho, M. S. Krass, M. Grabmair, Context-Aware Legal Citation Recommendation using Deep Learning, Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law (ICAIL 2021), 79-88, ACM, 2021. [arxiv]
  • J. Savelka, H. Westermann, K. Benyekhlef, C. S. Alexander, J. C. Grant, D. Restrepo Amariles, R. El-Hamdani, S. Meeus, A. Troussel, M. Araszkiewicz, K. D. Ashley, A. Ashley, K. L. Branting, M. Falduti, M. Grabmair, J. Harasta, T. Novotna, E. Tippett and S. Johnson, Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains,  Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law (ICAIL 2021), 129-138, ACM, 2021.