# The Effects of Demographic Instructions on LLM Personas

arXiv: https://arxiv.org/abs/2505.11795 · HTML: https://mlsanity.com/paper/2505.11795/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2025.

## Built on by (most cited first, 5 of 5)

- [Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detection](https://mlsanity.com/paper/2507.10996/) (2025)
- [Localizing Persona Representations in LLMs](https://mlsanity.com/paper/2505.24539/) (2025)
- [Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation](https://mlsanity.com/paper/2608.10385/) (2026)
- [AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?](https://mlsanity.com/paper/2606.13696/) (2026)
- [PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems](https://mlsanity.com/paper/2608.28378/) (2026)

## Abstract (arXiv)

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.