Bias Detection and Mitigation

Within the realm of computational sociolinguistics, natural language processing (NLP) investigates the manifestation of cognitive biases in natural language texts. The NLP Group conducts research on the detection and mitigation of social bias,  political bias, and other media bias.

• Spliethöver et al. (2025). Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli, Maximilian Muschalik, Barbara Hammer, Eyke Hüllermeier, and Henning Wachsmuth. Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection. NAACL 2025.
• Spliethöver et al. (2024). Maximilian Spliethöver, Sai Nikhil Menon, and Henning Wachsmuth. Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness. ACL Findings 2024.
• Stahl et al. (2022). Maja Stahl, Maximilian Spliethöver, and Henning Wachsmuth. 2022. To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation. NLP+CSS 2022.
• Spliethöver and Wachsmuth (2021). Maximilian Spliethöver and Henning Wachsmuth. Bias Silhouette Analysis: Towards Assessing the Quality of Bias Metrics for Word Embedding Models. IJCAI 2021.
• Chen et al. (2020). Wei-Fan Chen, Khalid Al Khatib, Benno Stein, and Henning Wachsmuth. Detecting Media Bias in News Articles using Gaussian Bias Distributions. EMNLP Findings 2020.

• Chen (2024): Wei-Fan Chen. Computational Analysis and Mitigation of Textual Media Bias. January 26, 2024. 

• NRW Project (2020–2022):  Bias in AI Models
• DFG-CRF 901 Subproject B1 (2019–2023): Parameterized Service Configurations