Papers › Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings

Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings

25 Nov 2024arXiv:2411.16527archive 2025-07-28

Carolin M. Schuster, Maria-Alexandra Dinisor, Shashwat Ghatiwala, Georg Groh

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.

PaperPDFCode

Code

carolinmschuster/profiling-bias-in-llms officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Word Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections