Work

The Effects of Demographic Instructions on LLM Personas

Year: 2025

Type: conference-paper

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.

Source: International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

DOI: 10.1145/3726302.3730255

Authors: Angel Felipe Magnossão de Paula, J. Shane Culpepper, Alistair Moffat, Sachin Pathiyan Cherumanal, Falk Scholer, Johanne Trippas

Institutions: Universitat Politècnica de València, The University of Queensland, The University of Melbourne, RMIT University

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDGs: Reduced inequalities, Gender equality

Open Access status: hybrid

Funder: RMIT University