Welcome!

I am an enthusiastic computer scientist from Lüdenscheid and work as a PhD student and research associate in the Semantic Computing Group at the Center for Cognitive Interaction Technology (CITEC) at Bielefeld University. My research as part of the SAIL project ("SustAInable Life-cycle of Intelligent Socio-Technical Systems") deals with issues in the area of Question Answering over Linked Data, Semantic Web, Lexical Knowledge and Compositionality in AI. My research interests can be found at "research".

I graduated from TU Dortmund University with a Master of Science with honours in Computer Science (minor in German Studies) in March 2023. A short CV can be found at "about me".

I am always happy to exchange ideas with other researchers and like-minded people, whether for networking, possible collaborations, or discussing technical or other topics.

Picture of David M. Schmidt from Lüdenscheid, Germany

Research Interests

Question Answering over Linked Data

Lexcial Knowledge

Compositionality in AI

  • Testing the limits of the compositional abilities of LLMs by operationalizing the systematicity and productivity properties as described by Szabó, Z. G. (2012)
  • Development of a dataset and compositionality metric for testing the systematicity property of LLMs in the context of QALD, exploring both in-context learning and fine-tuning

Structure Generation & Information Extraction

Social Media Listening for Quality of Life Estimation

About me

Curriculum Vitae

Hobbies and Volunteer Work

Current

  • Since 2015
    2015-2016 participant of the annual events of Jugend hackt under the motto "Make the world a better place with code", since 2017 support as mentor
  • Playing the piano since 2004 and the guitar since 2013

Former

Publications

A list of publications that I have contributed to:

2025

  • Nair, R. A. S., Hartung, M., Heinisch, P., Jaskolski, J., Starke-Knäusel, C., Veríssimo, S., Schmidt, D. M., & Cimiano, P. (2025). Summarizing online patient conversations using generative language models: Experimental and comparative study. JMIR Medical Informatics, 13, e62909. https://doi.org/10.2196/62909
  • Sanchez-Graillet, O., Schmidt, D. M., Kullik, C., & Cimiano, P. (2025). Open challenges for the automatic synthesis of clinical trials. BMC Research Notes, 18(1), 50. https://doi.org/10.1186/s13104-025-07121-6
    [tool]
  • Schmidt, D. M., & Cimiano, P. (2025). Grammar-constrained decoding for structured information extraction with fine-tuned generative models applied to clinical trial abstracts. Frontiers in Artificial Intelligence, 7, 1406857. https://doi.org/10.3389/frai.2024.1406857
    [artifact] [repo]

2024

  • Schmidt, D. M., Elahi, M. F., & Cimiano, P. (2025). Lexicalization is all you need: Examining the impact of lexical knowledge in a compositional QALD system. In M. Alam, M. Rospocher, M. van Erp, L. Hollink, & G. A. Gesese (Eds.), Knowledge Engineering and Knowledge Management (pp. 102–122). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-77792-9_7
    [preprint] [artifact] [repo] [docker]
  • Schmidt, D. M., & Cimiano, P. (2024). Question answering from healthcare fora. DataNinja sAIOnARA Conference, DataNinja sAIOnARA 2024 Conference. https://doi.org/10.11576/DATANINJA-1159
  • Witte, C.*, Schmidt, D. M.*, & Cimiano, P. (2024). Comparing generative and extractive approaches to information extraction from abstracts describing randomized clinical trials. Journal of Biomedical Semantics, 15(1), 3. https://doi.org/10.1186/s13326-024-00305-2
    [artifact] [repo]

2021

  • Jasper, M., Schlüter, M., Schmidt, D., & Steffen, B. (2021). Every component matters: Generating parallel verification benchmarks with hardness guarantees. In T. Margaria & B. Steffen (Eds.), Leveraging Applications of Formal Methods, Verification and Validation: Tools and Trends (Vol. 12479, pp. 242–263). Springer International Publishing. https://doi.org/10.1007/978-3-030-83723-5_16
  • Howar, F., Jasper, M., Mues, M., Schmidt, D., & Steffen, B. (2021). The RERS challenge: Towards controllable and scalable benchmark synthesis. International Journal on Software Tools for Technology Transfer, 23(6), 917–930. https://doi.org/10.1007/s10009-021-00617-z
* = Equal contribution to the publication

Articles and Reports (German)

Contact

I am always happy to get in contact with other enthusiastic and like-minded people. I can be reached best by an E-Mail to contact [at] davidmschmidt.de

Email symbol contact [at] davidmschmidt.de

Research

ORCID symbol DBLP symbol Google Scholar symbol Semantic Scholar symbol ResearchGate symbol

Social Media & Co.

LinkedIn symbol Bluesky symbol Mastodon symbol Twitter/X symbol GitHub symbol

Office

CITEC 2-310
Cognitive Interaction Technology Center (CITEC)
Universität Bielefeld
Inspiration 1
33619 Bielefeld
Germany

Postal Address

David M. Schmidt
Cognitive Interaction Technology Center (CITEC)
Universität Bielefeld
Inspiration 1
33619 Bielefeld
Germany