Dr. Jan Philip Wahle
Project Leader
SHORT BIO
Dr. Jan Philip Wahle is a faculty member at the University of Göttingen. He has been a visiting researcher at the National Research Council Canada (NRC) working with Dr. Saif M. Mohammad. Before his PhD, he worked as a software engineer for the autonomous driving company Aptiv PLC. His main research interests lie in computational linguistics and natural language processing with a focus on reasoning methods via reinforcement learning and agentic systems and AI safety via interpretability. His research has been presented at various conferences, including ACL and EMNLP, and won the ACL Best Resource Paper Award and the SemEval Best Task Award.
PROJECTS
I am open to student projects in the areas of computational linguistics and natural language processing, particularly involving reasoning methods via reinforcement learning and agentic systems and AI safety via interpretability. The slides here are examples of projects that I offer. Don’t hesitate to get in touch with me if you are interested.
SHORT CV
09/2025 – present
Project Leader & Research Fellow
Chair for Scientific Information Analytics, University of Göttingen
10/2022 – 11/2025
Scientific Staff Member
Chair for Scientific Information Analytics, University of Göttingen
09/2021 – 11/2025
Dr. rer. nat, Computer Science
Chair for Scientific Information Analytics, University of Göttingen
07/2020 – 11/2025
Lab Engineer
Chair for Data & Knowledge Engineering, University of Wuppertal
10/2018 – 10/2020
M.Sc., Computer Science (Data Analytics)
Chair for Data & Knowledge Engineering, University of Wuppertal
03/2017 – 10/2018
Junior Software Engineer
Aptiv PLC Wuppertal, Germany
10/2015 – 10/2018
B. Sc., Information Technology (Information Science)
University of Wuppertal
SELECTED PUBLICATIONS
A complete list of my publications is available here.
TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
D. Meier, J. P. Wahle, P. Röttger, T. Ruas, B. Gipp
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
SPaRC: A Spatial Pathfinding Reasoning Challenge
L.B. Kaesberg, J. P. Wahle, T. Ruas, B. Gipp
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
Paraphrase Types Elicit Prompt Engineering Capabilities
J. P. Wahle, T. Ruas, Y. Xu, B. Gipp
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields
J. P. Wahle, T. Ruas, M. Abdalla, B. Gipp, S. M. Mohammad
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
Paraphrase Types for Generation and Detection
J. P. Wahle, T. Ruas, B. Gipp
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
How Large Language Models are Transforming Machine-Paraphrase Plagiarism
J. P. Wahle, T. Ruas, F. Kirstein, B. Gipp
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)
(PDF DOI BibTeX)
Identifying Machine-Paraphrased Plagiarism
J. P. Wahle, T. Ruas, T. Foltynek, N. Meuschke, B. Gipp
Information for a Better World: Shaping the Global Future – 17th International Conference, iConference 2022.
(PDF DOI BibTeX)
Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection
J. P. Wahle, T. Ruas, N. Meuschke, B. Gipp
ACM/IEEE Joint Conference on Digital Libraries, JCDL 2021, Champaign, IL, USA, September 27-30, 2021
(PDF DOI BibTeX)
MEDIA COVERAGE
GippLab Joins International Research Project to Detect Fake News
How can AI help reliably identify falsified and manipulated digital content such as deepfakes, synthetic voices, and multimodal misinformation? This question is at the center of the Korean National Police Academy’s fake news project, a joint initiative involving the State Criminal Police Office, University [...]
Congratulations to Jan Philip Wahle on his successful PhD thesis defense
We are thrilled to announce that Jan Philip Wahle has successfully defended his PhD thesis titled Language Modeling and Understanding Through Paraphrase Generation and Detection. In the presence of his family, friends, and colleagues, Jan Philip delivered an outstanding presentation [...]
Lower Saxony Funds Project on AI in Museums with €2.25 Million
How can artificial intelligence (AI) support museums in digitally unlocking their collections? This question is being addressed by the joint project “AI in Museums”, in which our lab is involved. The Lower Saxony Ministry of Science and Culture (MWK) is [...]
