Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future of Edemorcacy

This paper investigates the use of Large Language Models (LLMs) to synthesize public opinion data, addressing challenges in traditional survey methods like declining response rates and non-response bias. We introduce a novel technique: role creation through knowledge injection, a form of in-context learning that leverages Retrieval-Augmented Generation (RAG) alongside HEXACO personality profiles and demographic data to generate personalized prompts dynamically. This method allows LLMs to simulate diverse opinions more accurately than existing prompt engineering approaches. We compare our results with pre-trained models with standard few-shot prompts. Experiments using questions from the Cooperative Election Study (CES) demonstrate that our role-creation approach significantly improves the alignment of LLM-generated opinions with realworld human survey responses, increasing answer adherence. In addition, we discuss challenges, limitations and future research directions.