使用LLM合成公众意见：角色创建、影响及电子民主的未来
Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy
AI总结：
本文提出基于知识注入的LLM角色创建方法，结合RAG与HEXACO人格档案动态生成提示，显著提升了合成公众意见与真实调查回应的一致性。
摘要：
本文研究了使用大型语言模型（LLM）合成公众意见数据，以解决传统调查方法中回应率下降和无回应偏差等挑战。我们引入了一种新技术：基于知识注入的角色创建，这是一种上下文学习形式，利用RAG和来自HEXACO模型的特定人格档案及人口统计信息，并将其用于动态生成的提示。该方法使LLM能比现有提示工程方法更准确地模拟多样化意见。我们将结果与使用标准少样本提示的预训练模型进行比较。使用合作选举研究（CES）问题的实验表明，我们的角色创建方法显著提升了LLM生成意见与现实人类调查回应的一致性，提高了答案遵从度。此外，我们讨论了挑战、局限性和未来研究方向。
英文摘要：
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 based on knowledge injection, a form of in-context learning that leverages RAG and specified personality profiles from the HEXACO model and demographic information, and uses that for dynamically generated prompts. 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 real-world human survey responses, increasing answer adherence. In addition, we discuss challenges, limitations and future research directions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
