Research Group Michael Hedderich
Michael Hedderich
Dr.
JRG Leader Human-Centered NLP
Michael Hedderich
leads the MCML Junior Research Group ‘Human-Centered NLP’ at LMU Munich.
His team’s research covers the intersection of machine learning, natural language processing (NLP) and human-computer interaction. Human factors have a crucial interplay with modern AI and NLP development, from the way data is obtained, e.g. in low-resource scenarios, to the need to understand and control models, e.g. through global explainability methods. AI technology also does not exist in a vacuum but must be validated together with the application experts and stakeholders it should serve. The group explores these questions from different perspectives, taking the lense of machine learning, natural language processing and human-computer interaction. By embracing these diverse perspectives, the researcher value how each viewpoint enriches the understanding of the same issues and how different skill sets complement one another.
Team members @MCML
PhD Students
Florian Eichin
→ Group Michael Hedderich
AI and Computational Linguistics
Jana Grimm
→ Group Barbara Plank
AI and Computational Linguistics
→ Co-Group Michael Hedderich
Raoyuan Zhao
→ Group Michael Hedderich
AI and Computational Linguistics
Recent News @MCML
Publications @MCML
2026
[22]
F. Eichin • Y. Du • P. Mondorf • M. Matveev • B. Plank • M. A. Hedderich
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
[21]
S. Ostermann • D. Gurgurov • T. Baeumel • M. A. Hedderich • S. Lapuschkin • W. Samek • V. Schmitt
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
[20]
H. Yu • T. Xu • M. A. Hedderich • W. Hamidouche • S. W. Zamir • D. I. Adelani
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL URL
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL URL
[19]
R. Zhao • Y. Liu • L. Altinger • H. Schütze • M. A. Hedderich
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL GitHub
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors.
ACL 2026 - 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL GitHub
[18]
Y. Liu • R. Zhao • H. Schütze • M. A. Hedderich
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
[17]
R. S.-E. Shim • K. Choi • K. Chang • M.-H. Hsu • F. Eichin • Z. Wu • A. Suhr • M. A. Hedderich • D. Harwath • D. R. Mortensen • B. Plank
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
[16]
J. Lan • Z. Liu • U. Schlegel • R. Zhao • Y. Liu • H. Schütze • M. A. Hedderich • T. Seidl
Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. arXiv
Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. arXiv
[15]
F. Körner • M. Matveev • F. Eichin • G. Kutyniok • B. Plank • M. A. Hedderich
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining.
Preprint (Apr. 2026). arXiv
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining.
Preprint (Apr. 2026). arXiv
[14]
P. H. L. de Araujo • M. A. Hedderich • A. Modarressi • H. Schütze • B. Roth
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions.
EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
[13]
R. Zhao • Y. Liu • H. Schütze • M. A. Hedderich
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages.
Findings @EACL 2026 - Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026. DOI
[12]
L. Hegemann • X. Wen • M. A. Hedderich • T. Nurmi • H. Subramonyam
ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent.
Preprint (Feb. 2026). arXiv
ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent.
Preprint (Feb. 2026). arXiv
2025
[11]
J. O. Alabi • M. A. Hedderich • D. I. Adelani • D. Klakow
Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead.
EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
[10]
F. Eichin • C. Schuster • G. Groh • M. A. Hedderich
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
[9]
R. Zhao • B. Chen • B. Plank • M. A. Hedderich
MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
[8]
R. Zhao • A. Köksal • A. Modarressi • M. A. Hedderich • H. Schütze
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing.
Findings @EMNLP 2025 - Findings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. DOI
[7]
F. Eichin • Y. J. Liu • B. Plank • M. A. Hedderich
Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI
Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI
[6]
M. A. Hedderich • A. Wang • R. Zhao • F. Eichin • J. Fischer • B. Plank
What’s the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI
What’s the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI
2024
[5]
J. Shin • A. Khatri • M. A. Hedderich • A. Lucero • A. Oulasvirta
Facilitating Asynchronous Idea Generation and Selection with Chatbots.
OZCHI 2024 - 36th Australian Conference on Human-Computer Interaction. Brisbane, Australia, Nov 30-Dec 04, 2024. DOI
Facilitating Asynchronous Idea Generation and Selection with Chatbots.
OZCHI 2024 - 36th Australian Conference on Human-Computer Interaction. Brisbane, Australia, Nov 30-Dec 04, 2024. DOI
[4]
B. Ma • X. Wang • T. Hu • A.-C. Haensch • M. A. Hedderich • B. Plank • F. Kreuter
The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models.
Findings @EMNLP 2024 - Findings of the Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA, Nov 12-16, 2024. DOI
The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models.
Findings @EMNLP 2024 - Findings of the Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA, Nov 12-16, 2024. DOI
[3]
R. Zhao • A. Köksal • Y. Liu • L. Weissweiler • A. Korhonen • H. Schütze
SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists.
Findings @EMNLP 2024 - Findings of the Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA, Nov 12-16, 2024. DOI GitHub
SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists.
Findings @EMNLP 2024 - Findings of the Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA, Nov 12-16, 2024. DOI GitHub
[2]
Q. Chen • X. Wang • P. Mondorf • M. A. Hedderich • B. Plank
Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination.
Preprint (Oct. 2024). arXiv
Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination.
Preprint (Oct. 2024). arXiv
[1]
J. Shin • M. A. Hedderich • B. J. Rey • A. Lucero • A. Oulasvirta
Understanding Human-AI Workflows for Generating Personas.
DIS 2024 - ACM Conference on Designing Interactive Systems. Copenhagen, Denmark, Jul 01-05, 2024. DOI
Understanding Human-AI Workflows for Generating Personas.
DIS 2024 - ACM Conference on Designing Interactive Systems. Copenhagen, Denmark, Jul 01-05, 2024. DOI
©all images: LMU | TUM
Back to Top
2024-12-27 - Last modified: 2026-07-01