Safety
Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions
arXiv:2609.38555v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in culturally sensitive settings, where alignment requires representing diverse preferences within po
arXiv:2609.38555v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in culturally sensitive settings, where alignment requires representing diverse preferences within populations. Yet existing methods model populations at coarse demographic or community levels and overlook within-group variation. We introduce Demographic Pluralism, an inference-time framework that estimates population-level opinion distributions without opinion-distribution training data or task-specific fine-tuning by generating multiple perspectives within demographically grounded groups. Across four backbones on GlobalOpinionQA and VITAL, it reduces Jensen-Shannon distance by 8.4%-26.4% over Modular Pluralism. Among weighted, equal-weighted, and inverse-weighted aggregation, equal weighting performs best overall; group-level error also increases with group weight, helping explain weighted aggregation's weaker performance.
Related
- VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
- Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
- Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
Source: arXiv cs.AI | 2026-10-01