Auditing Large Language Models for Enhanced Text-Based Stereotype Detection and Probing-Based Bias Evaluation

arXiv:2404.01768v1 Announce Type: new
Abstract: Recent advancements in Large Language Models (LLMs) have significantly increased their presence in human-facing Artificial Intelligence (AI) applications. However, LLMs could reproduce and even exacerbate stereotypical outputs from training data. This work introduces the Multi-Grain Stereotype (MGS) dataset, encompassing 51,867 instances across gender, race, profession, religion, and stereotypical text, collected by fusing multiple previously publicly available stereotype detection datasets. We explore different machine learning approaches aimed at establishing baselines for stereotype detection, and fine-tune several …

abstract applications artificial artificial intelligence arxiv bias cs.ai cs.cl data dataset detection evaluation however human instances intelligence language language models large language large language models llms stereotype text training training data type work