all AI news
Projective Methods for Mitigating Gender Bias in Pre-trained Language Models
March 28, 2024, 4:48 a.m. | Hillary Dawkins, Isar Nejadgholi, Daniel Gillis, Judi McCuaig
cs.CL updates on arXiv.org arxiv.org
Abstract: Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods, developed for word embeddings, can help when applied to BERT's internal representations. Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We evaluate the efficacy of …
abstract arxiv attention bias cs.cl embeddings gender gender bias history language language models nlp study type word word embeddings
More from arxiv.org / cs.CL updates on arXiv.org
Benchmarking LLMs via Uncertainty Quantification
2 days, 6 hours ago |
arxiv.org
CARE: Extracting Experimental Findings From Clinical Literature
2 days, 6 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineering Manager, Generative AI - Characters
@ Meta | Bellevue, WA | Menlo Park, CA | Seattle, WA | New York City | San Francisco, CA
Senior Operations Research Analyst / Predictive Modeler
@ LinQuest | Colorado Springs, Colorado, United States