Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings

2024/11/25 by Carolin Schuster, Maria-Alexandra Dinisor, Schuster, Carolin M. +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Natural Language Processing Techniques #Text Readability and Simplification

paper · pdf · doi:10.48550/arxiv.2411.16527

openalex publication_date 2024/11/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• STEREODISCO: Discovering Stereotypicality in LLMs

Related

• Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approach
• A Taxonomy of Stereotype Content in Large Language Models
• Measuring Stereotype and Deviation Biases in Large Language Models
• Gender Biases in LLMs: Higher intelligence in LLM does not necessarily solve gender bias and stereotyping
• Gender bias and stereotypes in Large Language Models