Dr. Stefan Arnold

Dr. Stefan Arnold

Akademischer Rat
Raum: Raum 5.439
Lange Gasse 20
90403 Nürnberg
Deutschland

Sprechzeiten

Nach Vereinbarung über Zoom: https://fau.zoom.us/j/97869596522

Research

  • Differential Privacy
  • (Mechanistic) Interpretbility
  • Language Models

Publications

  • Tobias Clement, Truong Nguyen, and Stefan Arnold. 2026. Towards Quantifying Compliance with the EU AI Act. In 59th Hawaii International Conference on System Sciences (HICCS 26). Maui, Hawaii. IEEE Computer Society.
  • Stefan Arnold and Dilara Yesilbas. 2025. Demystifying Block-cyclic Sampling for Federated Learning using MNIST. In 3nd International Conference on Federated Learning Technologies and Applications (FLTA 25). IEEE Computer Society.
  • Stefan Arnold. 2024. Stereotypical Bias peaks in First Responses of DALL-E3. In Proceedings of the 19th International Conference on Wirtschaftsinformatik (WI 24). Würzburg, Germany. Association for Information Systems.
  • Dilara Yesilbas, Stefan Arnold, and Alex Felker. 2022. Rethinking Pre-Training in Industrial Quality Control. In Proceedings of the 17th International Conference on Wirtschaftsinformatik (WI 22). Nuremberg, Germany. Association for Information Systems.

  • Stefan Arnold and Rene Gröbner. 2025. Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2. In Proceedings of the Eighth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP,  Suzhou, China. Association for Computational Linguistics.
  • Stefan Arnold. 2025. Memorization in Language Models through the Lens of Intrinsic Dimension. In Proceedings of the First Workshop on Large Language Model Memorization, Vienna, Austria. Association for Computational Linguistics.
  • Stefan Arnold. 2025. Inspecting the Representation Manifold of Differentially-Private Text. In Proceedings of the Sixth Workshop on Privacy in Natural Language Processing, Albuquerque, New Mexico. Association for Computational Linguistics.
  • Stefan Arnold, Marian Fietta, and Dilara Yesilbas. 2024. Routing in Sparsely-gated Language Models responds to Context. In Proceedings of the Seventh BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP,  Miami, Florida. Association for Computational Linguistics.
  • Stefan Arnold, Rene Gröbner, and Annika Schreiner. 2024. Characterizing Stereotypical Bias from Privacy-preserving Pre-Training. In Proceedings of the Fifth Workshop on Privacy in Natural Language Processing, Bangkok, Thailand. Association for Computational Linguistics.
  • Stefan Arnold, Nils Kemmerzell, and Annika Schreiner. 2023. Disentangling the Linguistic Competence of BERT subjected to Text-to-Text Privatization. In Proceedings of the Sixth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP,  Singapore, Singapore. Association for Computational Linguistics.
  • Stefan Arnold, Dilara Yesilbas, and Sven Weinzierl. 2023. Driving Context into Text-to-Text Privatization. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing, Toronto, Canada. Association for Computational Linguistics.
  • Stefan Arnold, Dilara Yesilbas, and Sven Weinzierl. 2023. Guiding Text-to-Text Privatization by Syntax. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing, Toronto, Canada. Association for Computational Linguistics.

  • Stefan Arnold, Dilara Yesilbas, Rene Gröbner, Dominik Riedelbauch, Maik Horn, and Sven Weinzierl. 2024. Documentation Practices of Artificial Intelligence. arXiv preprint arXiv:2406.18620.
  • Josephine Fischer, Stefan Arnold, and Dilara Yesilbas. 2023. Crowd-Powered Medical Diagnosis: The Potential of Crowdsourcing for Patients with Rare Diseases.
  • Stefan Arnold & Dilara Yesilbas. 2021. Demystifying the Effects of Non-Independence in Federated Learning. arXiv preprint arXiv:2103.11226.