Reasoning and predicting human opinions with large language models (LLMs) is essential yet challenging. Current methods employ role-playing with personae but face two major issues: LLMs are sensitive to even a single irrelevant persona, skewing predictions by up to 30%, and LLMs fail to reason strategically over personae. We propose Chain-of-Opinion (COO), a simple four-step solution modeling which and how to reason with personae, inspired by the Value--Belief--Norm (VBN) theory. COO differentiates between explicit personae (demographics and ideology) and implicit personae (historical opinions), involves: (1) filtering irrelevant attributes from explicit personae, (2) ranking implicit personae into a preferential list for selecting top-k, (3) applying novel VBN reasoning to extract user environmental and personal value, belief, and norm variables for accurate and reliable predictions, and (4) iterating VBN reasoning with progressively larger lists of implicit personae to handle potential persona insufficiency. COO efficiently achieves new state-of-the-art opinion prediction via prompting with only 5 inference calls, improving prior techniques by up to 4%. Notably, fine-tuning LMs with COO data results in significantly better opinion-aligned models, by up to 23%.

翻译：利用大语言模型（LLMs）对人类观点进行推理与预测至关重要，但也充满挑战。现有方法通过角色扮演使用人物设定，但面临两大问题：LLMs对单个不相关角色设定极为敏感，可导致预测偏差高达30%；且LLMs无法对角色设定进行策略性推理。受价值-信念-规范（VBN）理论启发，我们提出观点链（COO）——一个简单的四步解决方案，用于建模应选择哪些角色设定及如何进行推理。COO区分显性角色设定（人口统计特征与意识形态）与隐性角色设定（历史观点），其步骤包括：（1）从显性角色设定中过滤无关属性；（2）将隐性角色设定排序为偏好列表并选取前k个；（3）应用新颖的VBN推理提取用户的环境与个人价值、信念及规范变量，以实现准确可靠的预测；（4）使用逐步扩大的隐性角色设定列表迭代进行VBN推理，以处理潜在的角色设定不足问题。COO仅需5次推理调用即可通过提示高效实现新的最先进观点预测性能，将现有技术提升高达4%。值得注意的是，使用COO数据对语言模型进行微调可显著提升模型与观点对齐的程度，改进幅度高达23%。