Home  | Research | Groups | Hedderich

Research Group Michael Hedderich


Link to website at LMU PI Matchmaking

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

Link to website

Florian Eichin

Link to website

Jana Grimm

Link to website

Raoyuan Zhao

Recent News @MCML

Link to MCML-LAMARR Workshop at University of Bonn

08.10.2025

MCML-LAMARR Workshop at University of Bonn

Collaborating on NLP Research in Bonn

Link to MCML at ACL 2025

25.07.2025

MCML at ACL 2025

37 Accepted Papers (17 Main, 8 Findings, and 12 Workshops)

Link to MCML at EMNLP 2024

10.11.2024

MCML at EMNLP 2024

22 Accepted Papers (6 Main, 14 Findings, and 2 Workshops)

Link to MCML at DIS 2024

29.06.2024

MCML at DIS 2024

Two Accepted Papers

Publications @MCML

2025


[15] A* Conference
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. To be published. Preprint available. arXiv

[14]
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. To be published. Preprint available. arXiv

[13]
R. ZhaoB. ChenB. PlankM. 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. To be published. Preprint available. arXiv

[12]
R. ZhaoA. KöksalA. ModarressiM. A. HedderichH. 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. To be published. Preprint available. arXiv

[11]
J. Lan • Z. Liu • U. SchlegelR. ZhaoY. LiuH. SchützeM. A. HedderichT. Seidl
Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering.
Preprint (Oct. 2025). arXiv

[10]
Y. LiuR. Zhao • L. Altinger • H. SchützeM. A. Hedderich
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors.
Preprint (Oct. 2025). arXiv

[9]

[8] A* Conference
F. EichinY. J. LiuB. PlankM. 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. URL

[7] A* Conference
M. A. Hedderich • A. Wang • R. ZhaoF. 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. URL

[6]
F. Eichin • Y. Du • P. MondorfB. PlankM. A. Hedderich
Grokking ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior.
Preprint (May. 2025). arXiv GitHub

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

[4]
B. MaX. Wang • T. Hu • A.-C. HaenschM. A. HedderichB. PlankF. 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

[3]
R. ZhaoA. KöksalY. LiuL. Weissweiler • A. Korhonen • H. Schütze
SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic Evaluation.
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. WangP. MondorfM. A. HedderichB. Plank
Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination.
Preprint (Oct. 2024). arXiv

[1] A Conference
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