3 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.CL2025
Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models
Rebekka Görge, Michael Mock, Héctor Allende-Cid
Social categories and stereotypes are embedded in language and can introduce data bias into Large Language Models (LLMs). Despite safeguards, these biases often persist in model be…
cs.CL2024
LLMs and Memorization: On Quality and Specificity of Copyright Compliance
Felix B Mueller, Rebekka Görge, Anna K Bernzen +2
Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an imp…