The Effects of Demographic Instructions on LLM Personas
Journal:
arXiv
Published Date:
May 17, 2025
Abstract
Social media platforms must filter sexist content in compliance with
governmental regulations. Current machine learning approaches can reliably
detect sexism based on standardized definitions, but often neglect the
subjective nature of sexist language and fail to consider individual users'
perspectives. To address this gap, we adopt a perspectivist approach, retaining
diverse annotations rather than enforcing gold-standard labels or their
aggregations, allowing models to account for personal or group-specific views
of sexism. Using demographic data from Twitter, we employ large language models
(LLMs) to personalize the identification of sexism.
