Large language models (LLMs) are the foundation of the current successes of artificial intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks and encourage mitigation efforts these models need adequate and intuitive descriptions of their discriminatory properties, appropriate for all audiences of AI. We suggest bias profiles with respect to stereotype dimensions based on dictionaries from social psychology research. Along these dimensions we investigate gender bias in contextual embeddings, across contexts and layers, and generate stereotype profiles for twelve different LLMs, demonstrating their intuition and use case for exposing and visualizing bias.
@article{arxiv.2411.16527,
title = {Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings},
author = {Carolin M. Schuster and Maria-Alexandra Dinisor and Shashwat Ghatiwala and Georg Groh},
journal= {arXiv preprint arXiv:2411.16527},
year = {2025}
}