Using LLMs to Model the Beliefs and Preferences of Targeted Populations

arXiv:2403.20252v1 Announce Type: cross
Abstract: We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different applications, such as conducting simulated focus groups for new products, conducting virtual surveys, and testing behavioral interventions, especially for interventions that are expensive, impractical, or unethical. Existing work has had mixed success using LLMs to accurately model human …

abstract applications arxiv cs.ai cs.cl cs.lg focus human language language model large language large language model llm llms modeling population type