Exploring the limits of large language models as a reflection of human cognition: An illustration in the context of moral judgment.

Schröder S, Morgenroth T, Kuhl U, Vaquet V, Paaßen B (2026)
Technology, Mind, and Behavior.

Targeted Visualization of the Backbone of Encoder LLMs

Roberts J (I), Schulz A, Schröder S, Hermes L, Hammer B (2026)
In: Machine Learning and Principles and Practice of Knowledge Discovery in Databases. International Workshops of ECML PKDD 2024, Vilnius, Lithuania, September 9–13, 2024, Revised Selected Papers, Part II. Cerrato M, Kalinauskaitė D, Lukoševičius M, Pechenizkiy M, Šutienė K (Eds); Communications in Computer and Information Science. Cham: Springer Nature Switzerland: 82-97.

Linearity of Sensitive Concepts in Language Models

Schröder S, Vaquet V, Hammer B (2026)
In: ESANN 2026 proceesdings. Louvain-la-Neuve (Belgium): Ciaco - i6doc.com: 139-144.

Conceptualizing Uncertainty: A Concept-Based Approach to Explaining Uncertainty

Roberts I, Schulz A, Schröder S, Hinder F, Hammer B (2026)
In: Artificial Neural Networks and Machine Learning – ICANN 2026. 35th International Conference on Artificial Neural Networks, Padua, Italy, September 14–17, 2026, Proceedings, Part IV. Pasa L, Lintas A, Tetko IV, Micheli A, Navarin N, Villa AEP, Tortorella D, Polato M (Eds); Lecture Notes in Computer Science, 17092. Cham: Springer Nature Switzerland: 247-259.

Evaluating Concept Discovery Methods for Sensitive Attributes in Language Models

Schroeder S, Schulz A, Hammer B (2025)
In: ESANN 2025 proceedings. Louvain-la-Neuve (Belgium): Ciaco - i6doc.com: 669-674.

Large Language Models Do Not Simulate Human Psychology

Schroeder S, Morgenroth T, Kuhl U, Vaquet V, Paaßen B (2025)
arXiv.

Semantic Properties of Cosine Based Bias Scores for Word Embeddings

Schroeder S, Schulz A, Hinder F, Hammer B (2024)
In: Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods. Vol. 1. Setúbal, Portugal: SCITEPRESS - Science and Technology Publications: 160-168.

The SAME score: Improved cosine based measure for semantic bias

Schroeder S, Schulz A, Hammer B (2024)
In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE: 1-8.

So Can We Use Intrinsic Bias Measures or Not?

Schroeder S, Schulz A, Kenneweg P, Hammer B (2023)
In: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods. Setúbal, Portugal: SCITEPRESS - Science and Technology Publications: 403-410.

Debiasing Sentence Embedders Through Contrastive Word Pairs

Kenneweg P, Schroeder S, Schulz A, Hammer B (2023)
In: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods. Setúbal, Portugal: SCITEPRESS - Science and Technology Publications: 205-212.

Measuring Fairness with Biased Data: A Case Study on the Effects of Unsupervised Data in Fairness Evaluation

Schroeder S, Schulz A, Tarakanov I, Feldhans R, Hammer B (2023)
In: Advances in Computational Intelligence. 17th International Work-Conference on Artificial Neural Networks, IWANN 2023, Ponta Delgada, Portugal, June 19–21, 2023, Proceedings, Part I. Rojas I, Joya G, Catala A (Eds); Lecture Notes in Computer Science. Cham: Springer Nature Switzerland: 134-145.

Neural Architecture Search for Sentence Classification with BERT

Kenneweg P, Schroeder S, Hammer B (2022)
In: ESANN 2022 proceedings. Louvain-la-Neuve (Belgium): Ciaco - i6doc.com: 417-422.

Intelligent Learning Rate Distribution to Reduce Catastrophic Forgetting in Transformers

Kenneweg P, Schulz A, Schroeder S, Hammer B (2022)
In: Intelligent Data Engineering and Automated Learning – IDEAL 2022. 23rd International Conference, IDEAL 2022, Manchester, UK, November 24–26, 2022, Proceedings. Yin H, Camacho D, Tino P (Eds); Lecture Notes in Computer Science, 13756. Cham: Springer International Publishing: 252-261.