Simon Münker

Research Fellow at Trier University
mail linkedin github google scholar

I started my career as a media designer and front-end web developer (IHK), focusing on WordPress and reactive JavaScript while working on projects of various scales in finance, education, and health. During this time (2016), voice assistants and text-centric user interfaces began to rise. Thus, I decided to pivot my career and actively participate in the research and development of language processing techniques and generative text-based AI. I pursued an undergraduate in computational linguistics (2017) to complement my programming skills with a linguistic foundation. I continued my education with a master’s in natural language processing (2021), specializing in text analysis and generation with large language models. Afterward (2023), I joined the Department of Computational Linguistics at Trier University as a research fellow, focusing on language models as synthetic online social media users in the scope of an EU-funded research project.

Activities

Research

  • Kugler, K., Münker, S., Höhmann, J., & Rettinger, A. (2024). InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline. Journal of Computational Literary Studies, 2(1), Article 1. https://doi.org/10.48694/jcls.3572
  • Münker, S. (2023). Can Large Language Models replace human annotation for text classification? A comparison to prompt-based approaches on German Twitter data [Poster]. Patterns Poster-Session, University Trier
  • Münker, S. (2024). On the authenticity of generated OSN Content: Advances in Agent-based LLM prompting for persuasive posts [Presentation]. Patterns Early Career Forum, University Trier
  • Heseltine, M., Münker, S., Stolwijk, S., Trilling, D., & Oschatz, C. (2024). Generative User Content for Social Media Platforms: Comparing LLM Effectiveness and Approaches [Poster]. Etmaal 2024, Rotterdam
  • Münker, S. (2024). LLMs values towards digital Privacy: Exploring synthetic social media content from generated Agents [Poster]. Dagstuhl Seminar: Generative AI for Knowledge Engineering https://www.dagstuhl.de/24143
  • Münker, S., Kugler, K., & Rettinger, A. (2024). Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets. arXiv preprint arXiv:2406.18239
  • Münker, S. (2024). **Towards” Differential AI Psychology” and in-context Value-driven Statement Alignment with Moral Foundations Theory. arXiv preprint arXiv:2408.11415
  • Heseltine M., Münker S., Stolwijk S. (2024). Generative User Content for Social Media: LLM Effectiveness and Approaches. [Poster] American Political Science Association: Annual Meeting, Philadelphia

Teaching

  • Research Case Study: Aligning Language Models to the behavior of social media users [Student Research Group]. Winter Term 2023, Trier University
  • Algorithmische Methoden: Introduction to Python programming for text analysis [Exercise]. Winter Term 2023, Trier University
  • Natural Language Processing: Fundamentals of modern language processing with generative AI [Lecture & Exercise]. Summer Term 2024, Trier University
  • Anwendung der KI & CL - KI == Nutzer?: Critical Analysis of generative AI in social sciences [Guest Lecture]. Summer Term 2024, Trier University
  • Einführung in die Sprachwissenschaft: Fundamentals of contemporary (computational) linguistics [Lecture]. Winter Term 2024, Trier University

Posts

under construction