SHORT BIOGRAPHY

Jonas Becker is a PhD candidate at the Landeskriminalamt NRW. He earned his B.Sc. in Computer Science from the University of Wuppertal, where he conducted research on cross-document coreference resolution with a particular focus on media bias. He continued his academic training with an M.Sc. in Applied Computer Science, studying at the University of Wuppertal and later completing his degree at the University of Göttingen. During his master’s studies, he specialized in Natural Language Processing, working on paraphrase detection and transformer-based language models. Alongside his studies, he gained experience as a research assistant at both universities, contributing to projects in computational linguistics and agentic systems.

RESEARCH INTERESTS

Jonas Becker’s research centers on Natural Language Processing, with a particular focus on the reliability and safety of AI systems. His work investigates how language models and collaborative agents behave under challenging conditions, including performance degradation and strategic adversarial behavior in multi-agent environments.

His primary research interest topics are:

• Natural Language Processing
• Multi-Agent Systems
• AI Safety
• Text Generation and Large Language Models
• Detection of Machine-Generated Content
• Deep Learning
• Data Science

SHORT CV

12/2024 – present

Doctoral Researcher
LKA NRW & University of Göttingen

04/2022 – 12/2024

Applied Computer Science, M.Sc.
University of Wuppertal and since 2023 at the University of Göttingen, Germany

10/2017 – 03/2022

Computer Science, B.Sc.
University of Wuppertal, Germany

SELECTED PUBLICATIONS

Google Scholar

• L. B. Kaesberg, J. Becker, J. P. Wahle, T. Ruas, and B. Gipp, “Voting or Consensus? Decision-Making in Multi-Agent Debate,” in Findings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, 2025, pp. 11640-11671.
  [Bibtex]

  @inproceedings{Kaesberg2025,
    title     = {Voting or Consensus? Decision-Making in Multi-Agent Debate},
    author    = {Kaesberg, Lars Benedikt and Becker, Jonas and Wahle, Jan Philip and Ruas, Terry and Gipp, Bela},
    booktitle = {Findings of the 63rd Annual Meeting of the Association for
  Computational Linguistics (ACL)},
    month     = {July},
    year      = {2025},
    address   = {Vienna, Austria},
    publisher = {Association for Computational Linguistics},
    url       = {https://aclanthology.org/2025.findings-acl.606/},
    doi       = {10.18653/v1/2025.findings-acl.606},
    pages     = {11640 -- 11671},
    topic     = 
  }

• J. Becker, L. B. Kaesberg, N. Bauer, J. P. Wahle, T. Ruas, and B. Gipp, “MALLM: Multi-Agent Large Language Models Framework,” in Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 2025, pp. 418-439.
  [Bibtex]

  @inproceedings{Becker2025,
    title     = {{MALLM}: Multi-Agent Large Language Models Framework},
    author    = {Becker, Jonas  and Kaesberg, Lars Benedikt  and Bauer, Niklas  and Wahle, Jan Philip  and Ruas, Terry  and Gipp, Bela},
    year      = 2025,
    month     = 11,
    booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    address   = {Suzhou, China},
    pages     = {418--439},
    doi       = {10.18653/v1/2025.emnlp-demos.29},
    url       = {https://aclanthology.org/2025.emnlp-demos.29/},
    topic     = 
  }