用大模型多步推理预测美国总统选举，提升准确性。
Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models
- 设计多步推理框架，融合人口、意识形态与时间动态因素。
- 在2016和2020年美国选举研究数据上验证，表现优于传统方法。
- 适用于政治分析、选举预测研究者，尤其关注模型可解释性。
大型语言模型（LLMs）能否准确预测选举结果？尽管它们在医疗、法律和创意任务中表现出色，但在选举预测领域的潜力尚不明确。选举预测面临独特挑战：选民层级数据有限、政治环境快速变化、需建模复杂人类行为。为此，我们提出一种用于政治分析的多步推理框架。该方法在真实世界数据集美国国家选举研究（ANES）2016与2020年数据上进行验证，并结合由领先机器学习框架生成的合成人格数据，实现可扩展的选民行为建模。为捕捉时间动态，模型纳入候选人政策立场与生平信息，确保适应不断演变的政治背景。基于思维链提示（Chain of Thought prompting），我们的多步推理流程系统整合了人口统计、意识形态与时间依赖因素，显著提升了预测能力。
原文摘要 · Abstract (English)
Can Large Language Models (LLMs) accurately predict election outcomes? While LLMs have demonstrated impressive performance in various domains, including healthcare, legal analysis, and creative tasks, their ability to forecast elections remains unknown. Election prediction poses unique challenges, such as limited voter-level data, rapidly changing political landscapes, and the need to model complex human behavior. To address these challenges, we introduce a multi-step reasoning framework designed for political analysis. Our approach is validated on real-world data from the American National Election Studies (ANES) 2016 and 2020, as well as synthetic personas generated by the leading machine learning framework, offering scalable datasets for voter behavior modeling. To capture temporal dynamics, we incorporate candidates' policy positions and biographical details, ensuring that the model adapts to evolving political contexts. Drawing on Chain of Thought prompting, our multi-step reasoning pipeline systematically integrates demographic, ideological, and time-dependent factors, enhancing the model's predictive power.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。