en
Rebekka Görge
© Rebekka Görge
Rebekka Görge
ORCID iD 0009-0008-3793-1374
Show profile

Affiliations
  • Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS
Research topics
  • Technical methods for bias detection and mitigation
  • Large Language Models
  • Trustworthy AI
Rebekka Görge is a Senior Data Scientist at Fraunhofer Institute for Intelligent Analysis and Information Systems in Germany. Her research focuses on trustworthy artificial intelligence, particularly on the detection and mitigation of bias in large language models using sociolinguistic foundation, as well as the development of new approaches for the evaluation and auditing of AI systems. She is project lead of industry and research projects, such as "MISSION KI" (2024–2025), a large-scale initiative on trustworthy AI in Germany, and advises public authorities on the trustworthiness of AI. Moreover, she is an active trainer in the Fraunhofer Big Data Alliance for data science and trustworthy AI.
Selected publications

Rebekka Görge, Michael Mock, and Héctor Allende-Cid. 2025. Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (FAccT '25). Association for Computing Machinery, New York, NY, USA, 2796–2814. https://doi.org/10.1145/3715275.3732181

R. Görge, M. Mock and M. Akila, "Inspecting and Measuring Fairness of unlabeled Image Datasets," 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW), Utrecht, Netherlands, 2024, pp. 191-200, doi: 10.1109/ICDEW61823.2024.00031.

Mueller, F. B., Görge, R., Bernzen, A. K., Pirk, J. C., & Poretschkin, M. (2024). LLMs and Memorization: On Quality and Specificity of Copyright Compliance. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7(1), 984-996. https://doi.org/10.1609/aies.v7i1.31697.

Rebekka Görge
© Rebekka Görge
Rebekka Görge

-