2 papers
cs.CL2025
Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation
Rebekka Görge, Sujan Sai Gannamaneni, Tabea Naeven +10
Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations su…
cs.CV2025
Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions
Sujan Sai Gannamaneni, Rohil Prakash Rao, Michael Mock +2
Slice discovery methods (SDMs) are prominent algorithms for finding systematic weaknesses in DNNs. They identify top-k semantically coherent slices/subsets of data where a DNN-unde…