Matthias Aßenmacher

About

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 the Chair for Statistical Learning and Data Science (headed by Prof. Dr. Bernd Bischl) from early 2022 until late 2026 as a Postdoc, leading the Natural Language Processing focus group. Since October 2026, I have been leading the working group for Text Data and Statistical Language Technologies in the Department of Statistics at LMU Munich.

Matthias Aßenmacher

Contact

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

Teaching

My courses from Winter 2026/27 onwards can be found on my new homepage.

Past (Winter 21/22 - Summer 26):

Research Interests

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

Thesis supervision

I supervise theses on various NLP-related topics. Please see my new homepage.

You Can Find me on

References

  1. Braun L, Aßenmacher Mß Hohenadler M, Kauermann G (2026) Two Lawyers, Three Opinions: Can Output-Based LLM Uncertainty Find the Cases Where Experts Disagree? Accepted at the Third Workshop on Uncertainty-Aware NLP (EMNLP 2026),
  2. Kandlinger M, Ma B, Haensch A-C, Aßenmacher Mß(2026) Do LLMs Give Consistent Opinions? Evaluating Response Reliability Under Varying Likert-Scale Formulations in Survey-Style MCQA Accepted at the 11th Workshop on Natural User-generated Text (EMNLP 2026),
  3. Ding Y, Li M, Garces Arias E, Aßenmacher Mß Heumann C, Zhang C (2026) Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding Accepted at EMNLP 2026 Main Track,
  4. Zhang C, Wu S, Chen Y, Men Y, Fan G, Jiang Y, Aßenmacher Mß Heumann C (2026) Explainable Coarse-to-Fine Text-Centric Oracle Bone Duplicates Discovery Accepted to EMNLP 2026 System Demonstrations,
    link | pdf
  5. Garces Arias E, Sapargali N, Heumann C, Aßenmacher Mß(2026) The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices Accepted at INLG 2026,
  6. Gnadt K, Meidinger M, Aßenmacher Mß(2026) MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short Accepted at the GermEval Workshop on Harmful Content Detection,
  7. Leininger C, Veit H, Aßenmacher Mß Bender A (2026) Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Résumés [BIAS 2026] 6th Workshop on Bias and Fairness in AI at ECML PKDD,
    arXiv | pdf
  8. Ding Y, Li M, Garces Arias E, Aßenmacher Mß Heumann C, Zhang C (2026) Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14932–14948. Association for Computational Linguistics, San Diego, California, United States.
    link | pdf
  9. Chatterjee A, Schöffel M, Aßenmacher Mß Wiedner M, Garces Arias E (2026) Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities, pp. 276–296. Association for Computational Linguistics, San Diego, USA.
    link | pdf | doi
  10. Özeren E, Assenmacher Mss(2026) Reinforcement Learning for Latent-Space Thinking in LLMs Proceedings of the 11th Edition of the Swiss Text Analytics Conference, pp. 1–16. Association for Computational Linguistics, Zurich, Switzerland.
    link | pdf
  11. Loss G, Stephan A, Assenmacher Mss(2026) Enhancing Retrieval via Cognitively Motivated Document Expansion Proceedings of the 11th Edition of the Swiss Text Analytics Conference, pp. 17–28. Association for Computational Linguistics, Zurich, Switzerland.
    link | pdf
  12. Chen Z, Heumann C, Assenmacher Mss(2026) An Efficient Approach for Answering Not Readily Attainable Questions for RAG-based Applications Proceedings of the 11th Edition of the Swiss Text Analytics Conference, pp. 29–51. Association for Computational Linguistics, Zurich, Switzerland.
    link | pdf
  13. Zehle T, Aßenmacher Mß(2026) Can Calibration of Positional Encodings Enhance Long Context Utilization? Findings of the Association for Computational Linguistics: EACL 2026, pp. 2268–2280. Association for Computational Linguistics, Rabat, Morocco.
    link | pdf
  14. Zehle T, Heiß T, Schlager M, Aßenmacher Mß Feurer M (2026) promptolution: A Unified, Modular Framework for Prompt Optimization Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 282–296. Association for Computational Linguistics, Rabat, Marocco.
    link | pdf
  15. Urchs S, Thurner V, Aßenmacher Mß Heumann C, Thiemichen S (2025) Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems, pp. 55–65. Association for Computational Linguistics, Mumbai, India.
    link | pdf
  16. Amin M, Aßenmacher Mß(2025) Do Companies Reveal Their Own Fraud? - A Novel Data Set for Fraud Detection Based on 10-K Reports Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing, pp. 148–166. Association for Computational Linguistics, Suzhou, China.
    link | pdf | doi
  17. Gruber C, Alber H, Bischl B, Kauermann G, Plank B, Aßenmacher Mß(2025) Revisiting Active Learning under (Human) Label Variation Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP, pp. 75–86. Association for Computational Linguistics, Suzhou, China.
    link | pdf
  18. Ding Y, Garces Arias E, Li M, Rodemann J, Aßenmacher Mß Chen D, Fan G, Heumann C, Zhang C (2025) GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 7202–7226. Association for Computational Linguistics, Suzhou, China.
    link | pdf
  19. Garces Arias E, Blocher H, Rodemann J, Aßenmacher Mß Jansen C (2025) Statistical Multicriteria Evaluation of LLM-Generated Text Proceedings of the 18th International Natural Language Generation Conference, pp. 338–351. Association for Computational Linguistics, Hanoi, Vietnam.
    link | pdf
  20. Urchs S, Thurner V, Aßenmacher Mß 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 Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR, pp. 489–500. SciTePress.
    link | doi
  21. Garces Arias E, Blocher H, Rodemann J, Li M, Heumann C, Aßenmacher Mß(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.
    link | pdf
  22. Stephan A, Zhu D, Aßenmacher Mß 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
  23. Ma B, Yoztyurk B, Haensch A-C, Wang X, Herklotz M, Kreuter F, Plank B, Aßenmacher Mß(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
  24. Urchs S, Thurner V, Aßenmacher Mß 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
  25. Debelak R, Koch T, Aßenmacher Mß 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.
    pdf | doi
  26. Schöffel M, Garces Arias E, Wiedner M, Ruppert P, Li M, Heumann C, Aßenmacher Mß(2025) Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages arXiv preprint 2506.17715,
    link | pdf
  27. Rauch L, Wirth M, Huseljic D, Herde M, Sick B, Aßenmacher Mß(2025) No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success arXiv preprint 2506.01992,
    link | pdf
  28. Schöffel M, Wiedner M, Garces Arias E, Ruppert P, Heumann C, Aßenmacher Mß(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
  29. Wuttke A, Aßenmacher Mß 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
  30. Mironov M, Marquard A, Racek D, Heumann C, Thurner PW, Aßenmacher Mß(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
  31. Garces Arias E, Li M, Heumann C, Aßenmacher Mß(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
  32. Garces Arias E, Rodemann J, Li M, Heumann C, Aßenmacher Mß(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
  33. Aßenmacher Mß 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
  34. Urchs S, Thurner V, Aßenmacher Mß 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
  35. Aßenmacher Mß 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
  36. Mittermeier A, Aßenmacher Mß Schachtner B, Grosu S, Dakovic V, Kandratovich V, Sabel B, Ingrisch M (2024) Automatische ICD-10-Codierung. Die Radiologie, 1–7.
    link
  37. Deiseroth B, Meuer M, Gritsch N, Eichenberg C, Schramowski P, Aßenmacher Mß 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
  38. Mayer L, Heumann C, Aßenmacher Mß(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
  39. Aßenmacher Mß 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
  40. Solderer A, Hicklin S, Aßenmacher Mß 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.
    pdf | doi
  41. Gruber C, Hechinger K, Aßenmacher Mß 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
  42. Garces Arias E, Pai V, Schöffel M, Heumann C, Aßenmacher Mß(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 | doi
  43. Öztürk IT, Nedelchev R, Heumann C, Garces Arias E, Roger M, Bischl B, Aßenmacher Mß(2023) How Different Is Stereotypical Bias Across Languages? 3rd Workshop on Bias and Fairness in AI (co-located with ECML-PKDD 2023),
    link | pdf
  44. Witte M, Schwenzow J, Heitmann M, Reisenbichler M, Aßenmacher Mß(2023) Potential for Decision Aids based on Natural Language Processing Proceedings of the European Marketing Academy, 52nd, (114322),
    link | pdf
  45. Aßenmacher Mß 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
  46. 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 Mß(2023) Multimodal Deep Learning. arXiv preprint arXiv:2301.04856.
    link | pdf
  47. Koch P, Nuñez GV, Garces Arias E, Heumann C, Schöffel M, Häberlin A, Aßenmacher Mß(2023) A tailored Handwritten-Text-Recognition System for Medieval Latin First Workshop on Ancient Language Processing (ALP 2023),
    link | pdf
  48. Rauch L, Aßenmacher Mß 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
  49. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher Mß(2023) A Bayesian approach to modeling topic-metadata relationships. AStA Advances in Statistical Analysis 108, 333–349.
    link
  50. Urchs S, Thurner V, Aßenmacher Mß 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
  51. Vogel M, Aßenmacher Mß 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
  52. Aßenmacher Mß Dietrich M, Elmaklizi A, Hemauer EM, Wagenknecht N (2022) Whitepaper: New Tools for Old Problems.
    doi
  53. Koch P, Aßenmacher Mß 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
  54. Lebmeier E, Aßenmacher Mß 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.
    pdf
  55. Aßenmacher Mß 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),
  56. Aßenmacher Mß 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
  57. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher Mß Wankmüller S (2021) Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach. arXiv preprint arXiv:2104.02496.
    link | pdf
  58. Lebmeier E, Hou N, Spann K, Aßenmacher Mß(2021) Creating a Customer Centricity Graph from unstructured customer feedback. Applied Marketing Analytics 6, 221–229.
    link | pdf
  59. Meidinger M, Aßenmacher Mß(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 | doi
  60. Schiergens TS, Drefs M, Dörsch M, Kühn F, Albertsmeier M, Niess H, Schoenberg MB, Assenmacher Mss Küchenhoff H, Thasler WE, others (2021) Prognostic Impact of Pedicle Clamping during Liver Resection for Colorectal Metastases. Cancers 13, 72.
    link | pdf
  61. Guderlei M, Aßenmacher Mß(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
  62. Viellieber VD, Aßenmacher Mß(2020) Pre-trained language models as knowledge bases for Automotive Complaint Analysis. arXiv preprint arXiv:2012.02558.
    link | pdf
  63. Aßenmacher Mß 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
  64. Aßenmacher Mß 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
  65. Sint A, Lutz R, Assenmacher Mss 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
  66. Deffner V, Kreuzer M, Sobotzki C, Aßenmacher Mß 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
  67. Küchenhoff H, Deffner V, Aßenmacher Mß Neppl H, Kaiser C, Güthlin D, others (2018) Ermittlung der Unsicherheiten der Strahlenexpositionsabschätzung in der Wismut-Kohorte-Teil I-Vorhaben 3616S12223.
    link | pdf
  68. Brandl C, Breinlich V, Stark KJ, Enzinger S, Aßenmacher Mß 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
  69. Goschenhofer J, Ragupathy P, Heumann C, Bischl B, Aßenmacher Mß(2022) CC-Top: Constrained Clustering for Dynamic Topic Discovery Workshop on Ever Evolving NLP (EvoNLP), Association for Computational Linguistics, Abu Dhabi, United Arab Emirates.
    link | pdf