arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.06302cs.CY
收藏

大语言模型能跟踪公众意见吗?2024年美国总统选举中多模型对候选人好感度预测的分析

Do LLMs Track Public Opinion? A Multi-Model Study of Favorability Predictions in the 2024 U.S. Presidential Election

MIT(麻省理工学院);CMU(卡内基梅隆大学)

Riya Parikh, Sarah H. Cen, Chara Podimata

AI总结:

研究发现,现成的大语言模型在预测2024年美国总统选举候选人好感度时存在系统性偏差,且无法通过时间平滑或互联网增强检索进行纠正。

摘要:

我们研究了大型语言模型(LLMs)是否能通过退出民调来跟踪公众意见,特别是在2024年美国总统选举周期中。我们的分析聚焦于多个LLM在选举期间每日查询中对总统候选人好感度(例如“有利”vs.“不利”)的预测。使用公开可用的llm-election-data-2024数据集,我们评估了九种LLM配置对五个高质量民调的预测,这些民调来自主要组织包括路透社、CNN、盖洛普、昆尼皮亚克和ABC。我们发现存在系统性的方向性偏差。对于卡玛拉·哈里斯,所有模型都比民调高估了10-40%的好感度。对于唐纳德·特朗普,偏差较小(5-10%),并且依赖于民调,且跨模型变化显著较低。这些偏差在时间平滑下仍然存在,并且不被互联网增强检索纠正。我们得出结论,即现成的LLM在简单查询下无法可靠地跟踪民调,并讨论了其对选举预测的影响。

英文摘要:

We investigate whether Large Language Models (LLMs) can track public opinion as measured by exit polls during the 2024 U.S. presidential election cycle. Our analysis focuses on headline favorability (e.g., "Favorable" vs. "Unfavorable") of presidential candidates across multiple LLMs queried daily throughout the election season. Using the publicly available llm-election-data-2024 dataset, we evaluate predictions from nine LLM configurations against a curated set of five high-quality polls from major organizations including Reuters, CNN, Gallup, Quinnipiac, and ABC. We find systematic directional miscalibration. For Kamala Harris, all models overpredict favorability by 10-40% relative to polls. For Donald Trump, biases are smaller (5-10%) and poll-dependent, with substantially lower cross-model variation. These deviations persist under temporal smoothing and are not corrected by internet-augmented retrieval. We conclude that off-the-shelf LLMs do not reliably track polls when queried in a straightforward manner and discuss implications for election forecasting.

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。

↑