Score: 1

The Effects of Demographic Instructions on LLM Personas

Published: May 17, 2025 | arXiv ID: 2505.11795v1

By: Angel Felipe Magnossão de Paula , J. Shane Culpepper , Alistair Moffat and more

Potential Business Impact:

Helps social media spot sexism from different views.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇦🇺 🇪🇸 Australia, Spain

Page Count
5 pages

Category
Computer Science:
Information Retrieval