Matthias Aßenmacher

About

I am a postdoctoral researcher at the Chair of Statistical Learning and Data Science (SLDS, Dept. of Statistics, LMU) and the NFDI Consortium for Business, Economic and Related Data (BERD@NFDI). I obtained my bachelor’s degree in Economics from LMU in 2014, and my Master’s degree in Statistics (with a focus on social and economic studies) in 2017 (also from LMU). In 2021 I finished my PhD under the supervision of Prof. Dr. Christian Heumann with a focus on Natural Language Processing, before joining SLDS in early 2022. I lead the Natural Language Processing focus group at SLDS, and I am part of the Causal and Fair Machine Learning focus group. Further, I am one of the main maintainers of the course Deep Learning for NLP that is jointly developed at LMU Munich and the University of Vienna.

Contact

Department of Statistics, LMU Munich
Ludwigstraße 33, D-80539 München
firstname [at] stat [dot] uni [minus] muenchen [dot] de

Teaching

Past (since Winter 21/22):

Research Interests

My main research interest is NLP; For more details, see the NLP focus group page.

Thesis supervision

I supervise theses on various NLP-related topics. Please read the information on our focus group page before sending me an e-mail. A list of previously supervised theses and projects can also be found on the focus group page.

You Can Find me on

References

  1. Urchs S, Thurner V, Aßenmacher M, Bothmann L, Heumann C, Thiemichen S (2025) Are All Genders Equal in the Eyes of Algorithms? – Analysing Search and Retrieval Algorithms for Algorithmic Gender Fairness Accepted at: 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management,
    link|pdf    .
  2. Garces Arias E, Blocher H, Rodemann J, Aßenmacher M, Jansen C (2025) Statistical Multicriteria Evaluation of LLM-Generated Text Accepted at: 18th International Natural Language Generation Conference (INLG 2025),
    link|pdf    .
  3. Ding Y, Garces Arias E, Li M, Rodemann J, Aßenmacher M, Chen D, Fan G, Heumann C, Zhang C (2025) GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation Accepted at: Findings of the Association for Computational Linguistics: EMNLP 2025,
    link|pdf    .
  4. Urchs S, Thurner V, Aßenmacher M, Heumann C, Thiemichen S (2025) Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora arXiv preprint 2508.13169,
    link|pdf    .
  5. Garces Arias E, Blocher H, Rodemann J, Li M, Heumann C, Aßenmacher M (2025) Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM^2), pp. 631–654. Association for Computational Linguistics, Vienna, Austria and.
    link|pdf    .
  6. Stephan A, Zhu D, Aßenmacher M, Shen X, Roth B (2025) From Calculation to Adjudication: Examining LLM Judges on Mathematical Reasoning Tasks Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM^2), pp. 759–773. Association for Computational Linguistics, Vienna, Austria.
    link|pdf    .
  7. Ma B, Yoztyurk B, Haensch A-C, Wang X, Herklotz M, Kreuter F, Plank B, Aßenmacher M (2025) Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1785–1809. Association for Computational Linguistics, Vienna, Austria.
    link|pdf    .
  8. Urchs S, Thurner V, Aßenmacher M, Heumann C, Thiemichen S (2025) taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades Findings of the Association for Computational Linguistics: ACL 2025, pp. 10661–10671. Association for Computational Linguistics, Vienna, Austria.
    link|pdf    .
  9. Debelak R, Koch T, Aßenmacher M, Stachl C (2025) From Embeddings to Explainability: A Tutorial on Transformer-Based Text Analysis for Social and Behavioral Scientists. Advances in Methods and Practices in Psychological Science 8.
    link|pdf    .
  10. Gruber C, Alber H, Bischl B, Kauermann G, Plank B, Aßenmacher M (2025) Revisiting Active Learning under (Human) Label Variation Accepted at 4th Workshop on Perspectivist Approaches to NLP (EMNLP 2025),
    link|pdf    .
  11. Schöffel M, Garces Arias E, Wiedner M, Ruppert P, Li M, Heumann C, Aßenmacher M (2025) Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages arXiv preprint 2506.17715,
    link|pdf    .
  12. Rauch L, Wirth M, Huseljic D, Herde M, Sick B, Aßenmacher M (2025) No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success arXiv preprint 2506.01992,
    link|pdf    .
  13. Zhang C, Wu S, Chen Y, Aßenmacher M, Heumann C, Men Y, Fan G, Gama J (2025) OBD-Finder: Explainable Coarse-to-Fine Text-Centric Oracle Bone Duplicates Discovery arXiv preprint 2505.03836,
    link|pdf    .
  14. Schöffel M, Wiedner M, Garces Arias E, Ruppert P, Heumann C, Aßenmacher M (2025) Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pp. 334–349. Association for Computational Linguistics, Albuquerque, USA.
    link|pdf    .
  15. Wuttke A, Aßenmacher M, Klamm C, Lang MM, Würschinger Q, Kreuter F (2025) AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025), pp. 179–204. Association for Computational Linguistics, Albuquerque, New Mexico.
    link|pdf    .
  16. Mironov M, Marquard A, Racek D, Heumann C, Thurner PW, Aßenmacher M (2025) A Geoparsing Pipeline for Multilingual Social Media Posts from Ukraine Proceedings of The GeoExT 2025: Geographic Information Extraction from Texts Workshop co-located with The 47th European Conference on Information Retrieval (ECIR), Lucca, Italy.
    link|pdf    .
  17. Garces Arias E, Li M, Heumann C, Assenmacher M (2025) Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation Proceedings of the 31st International Conference on Computational Linguistics, pp. 9992–10020. Association for Computational Linguistics, Abu Dhabi, UAE.
    link|pdf    .
  18. Garces Arias E, Rodemann J, Li M, Heumann C, Aßenmacher M (2024) Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 15060–15080. Association for Computational Linguistics, Miami, Florida, USA.
    link|pdf    .
  19. Aßenmacher M, Karrlein L, Schiele P, Heumann C (2024) Introducing wwm-german-18k - Can LLMs Crack the Million? (Or Win at Least 500 Euros?) Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024), pp. 287–296. Association for Computational Linguistics, Trento.
    link|pdf    .
  20. Urchs S, Thurner V, Aßenmacher M, Heumann C, Thiemichen S (2024) Detecting Gender Discrimination on Actor Level Using Linguistic Discourse Analysis Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pp. 140–149. Association for Computational Linguistics, Bangkok, Thailand.
    link|pdf    .
  21. Aßenmacher M, Stephan A, Weissweiler L, Çano E, Ziegler I, Härttrich M, Bischl B, Roth B, Heumann C, Schütze H (2024) Collaborative Development of Modular Open Source Educational Resources for Natural Language Processing Proceedings of the Sixth Workshop on Teaching NLP, pp. 43–53. Association for Computational Linguistics, Bangkok, Thailand.
    link|pdf    .
  22. Mittermeier A, Aßenmacher M, Schachtner B, Grosu S, Dakovic V, Kandratovich V, Sabel B, Ingrisch M (2024) Automatische ICD-10-Codierung. Die Radiologie, 1–7.
    link    .
  23. Deiseroth B, Meuer M, Gritsch N, Eichenberg C, Schramowski P, Aßenmacher M, Kersting K (2024) Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 6764–6783. Association for Computational Linguistics, Mexico City, Mexico.
    link|pdf    .
  24. Mayer L, Heumann C, Aßenmacher M (2024) Can OpenSource beat ChatGPT? - A Comparative Study of Large Language Models for Text-to-Code Generation Proceedings of the 9th edition of the Swiss Text Analytics Conference, pp. 1–20. Association for Computational Linguistics, Chur, Switzerland.
    link|pdf    .
  25. Aßenmacher M, Sauter N, Heumann C (2024) Classifying multilingual party manifestos: Domain transfer across country, time, and genre Proceedings of the 9th edition of the Swiss Text Analytics Conference, pp. 21–31. Association for Computational Linguistics, Chur, Switzerland.
    link|pdf    .
  26. Solderer A, Hicklin S, Aßenmacher M, Ender A, Schmidlin P (2024) Influence of an allogenic collagen scaffold on implant sites with thin supracrestal tissue height: a randomized clinical trial. Clinical Oral Investigations, 28, 313.
    link|pdf    .
  27. Gruber C, Hechinger K, Aßenmacher M, Kauermann G, Plank B (2024) More Labels or Cases? Assessing Label Variation in Natural Language Inference Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language, pp. 22–32. Association for Computational Linguistics, Malta.
    link|pdf    .
  28. Garces Arias E, Pai V, Schöffel M, Heumann C, Aßenmacher M (2023) Automatic Transcription of Handwritten Old Occitan Language Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 15416–15439. Association for Computational Linguistics, Singapore.
    link|pdf    .
  29. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher M (2023) A Bayesian approach to modeling topic-metadata relationships. AStA Advances in Statistical Analysis 108, 333–349.
    link    .
  30. Koch P, Nuñez GV, Garces Arias E, Heumann C, Schöffel M, Häberlin A, Aßenmacher M (2023) A tailored Handwritten-Text-Recognition System for Medieval Latin Proceedings of the Ancient Language Processing Workshop, pp. 103–110. INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria.
    link|pdf    .
  31. Aßenmacher M, Rauch L, Goschenhofer J, Stephan A, Bischl B, Roth B, Sick B (2023) Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering Proceedings of the 7th Workshop on Interactive Adaptive Learning (co-located with ECML-PKDD 2023),
    link|pdf    .
  32. Urchs S, Thurner V, Aßenmacher M, Heumann C, Thiemichen S (2023) How Prevalent is Gender Bias in ChatGPT? - Exploring German and English ChatGPT Responses 1st Workshop on Biased Data in Conversational Agents (co-located with ECML-PKDD 2023),
    link|pdf    .
  33. Öztürk IT, Nedelchev R, Heumann C, Garces Arias E, Roger M, Bischl B, Aßenmacher M (2023) How Different Is Stereotypical Bias Across Languages? 3rd Workshop on Bias and Fairness in AI (co-located with ECML-PKDD 2023),
    link|pdf    .
  34. Rauch L, Aßenmacher M, Huseljic D, Wirth M, Bischl B, Sick B (2023) ActiveGLAE: A Benchmark for Deep Active Learning with Transformers Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023,
    link|pdf    .
  35. Witte M, Schwenzow J, Heitmann M, Reisenbichler M, Aßenmacher M (2023) Potential for Decision Aids based on Natural Language Processing Proceedings of the European Marketing Academy, 52nd, (114322),
    link|pdf    .
  36. Vogel M, Aßenmacher M, Gubler A, Attin T, Schmidlin PR (2023) Cleaning potential of interdental brushes around orthodontic brackets-an in vitro investigation. Swiss Dental Journal 133.
    link|pdf    .
  37. Akkus C, Chu L, Djakovic V, Jauch-Walser S, Koch P, Loss G, Marquardt C, Moldovan M, Sauter N, Schneider M, Schulte R, Urbanczyk K, Goschenhofer J, Heumann C, Hvingelby R, Schalk D, Aßenmacher M (2023) Multimodal Deep Learning. arXiv preprint arXiv:2301.04856.
    link|pdf    .
  38. Goschenhofer J, Ragupathy P, Heumann C, Bischl B, Aßenmacher M (2022) CC-Top: Constrained Clustering for Dynamic Topic Discovery Proceedings of the The First Workshop on Ever Evolving NLP (EvoNLP), pp. 26–34. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Hybrid).
    link|pdf    .
  39. Lebmeier E, Aßenmacher M, Heumann C (2022) On the current state of reproducibility and reporting of uncertainty for Aspect-based Sentiment Analysis Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), Springer International Publishing, Grenoble, France.
    link|pdf    .
  40. Aßenmacher M, Dietrich M, Elmaklizi A, Hemauer EM, Wagenknecht N (2022) Whitepaper: New Tools for Old Problems.
    link    .
  41. Koch P, Aßenmacher M, Heumann C (2022) Pre-trained language models evaluating themselves - A comparative study Proceedings of the Third Workshop on Insights from Negative Results in NLP, pp. 180–187. Association for Computational Linguistics, Dublin, Ireland.
    link|pdf    .
  42. Aßenmacher M, Schulze P, Heumann C (2021) Benchmarking down-scaled (not so large) pre-trained language models Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021), pp. 14–27. KONVENS 2021 Organizers, Düsseldorf, Germany.
    link|pdf    .
  43. Aßenmacher M, Corvonato A, Heumann C (2021) Re-Evaluating GermEval17 Using German Pre-Trained Language Models Proceedings of the Swiss Text Analytics Conference 2021, CEUR Workshop Proceedings, Winterthur, Switzerland (Online).
    link|pdf    .
  44. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher M, Wankmüller S (2021) Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach. arXiv preprint arXiv:2104.02496.
    link|pdf    .
  45. Lebmeier E, Hou N, Spann K, Aßenmacher M (2021) Creating a Customer Centricity Graph from unstructured customer feedback. Applied Marketing Analytics 6, 221–229.
    link|pdf    .
  46. Meidinger M, Aßenmacher M (2021) A New Benchmark for NLP in Social Sciences: Evaluating the Usefulness of Pre-trained Language Models for Classifying Open-ended Survey Responses Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, pp. 866–873. SciTePress.
    link|pdf    .
  47. Schiergens TS, Drefs M, Dörsch M, Kühn F, Albertsmeier M, Niess H, Schoenberg MB, Assenmacher M, Küchenhoff H, Thasler WE, others (2021) Prognostic Impact of Pedicle Clamping during Liver Resection for Colorectal Metastases. Cancers 13, 72.
    link|pdf    .
  48. Guderlei M, Aßenmacher M (2020) Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News Proceedings of the 28th International Conference on Computational Linguistics, pp. 6339–6349. International Committee on Computational Linguistics, Barcelona, Spain (Online).
    link|pdf    .
  49. Viellieber VD, Aßenmacher M (2020) Pre-trained language models as knowledge bases for Automotive Complaint Analysis. arXiv preprint arXiv:2012.02558.
    link|pdf    .
  50. Aßenmacher M, Heumann C (2020) On the comparability of pre-trained language models Proceedings of the 5th Swiss Text Analytics Conference and 16th Conference on Natural Language Processing, CEUR Workshop Proceedings, Zurich, Switzerland (Online).
    link|pdf    .
  51. Aßenmacher M, Kaiser JC, Zaballa I, Gasparrini A, Küchenhoff H (2019) Exposure-lag-response associations between lung cancer mortality and radon exposure in German uranium miners. Radiation and Environmental Biophysics.
    link|pdf    .
  52. Sint A, Lutz R, Assenmacher M, Küchenhoff H, Kühn F, Faist E, Bazhin AV, Rentsch M, Werner J, Schiergens TS (2019) Monocytic HLA-DR expression for prediction of anastomotic leak after colorectal surgery. Journal of the American College of Surgeons 229, 200–209.
    link    .
  53. Deffner V, Kreuzer M, Sobotzki C, Aßenmacher M, Güthlin D, Kaiser C, Küchenhoff H, Fenske N (2019) Uncertainties in radiation exposure assessment in the Wismut cohort: a preliminary evaluation BIO Web of Conferences, p. 03009. EDP Sciences.
    link|pdf    .
  54. Küchenhoff H, Deffner V, Aßenmacher M, Neppl H, Kaiser C, Güthlin D, others (2018) Ermittlung der Unsicherheiten der Strahlenexpositionsabschätzung in der Wismut-Kohorte-Teil I-Vorhaben 3616S12223.
    link|pdf    .
  55. Brandl C, Breinlich V, Stark KJ, Enzinger S, Aßenmacher M, Olden M, Grassmann F, Graw J, Heier M, Peters A, others (2016) Features of age-related macular degeneration in the general adults and their dependency on age, sex, and smoking: results from the German KORA study. PloS one 11, e0167181.
    link|pdf    .