大模型能精准预测全球气候行动支持度的感知差距
Large language models accurately predict public perceptions of support for climate action worldwide
- 用大模型分析125国民意，预测人们对他人支持度的误判
- Claude模型误差仅约5个百分点，相关性达0.77，媲美统计模型
- 适合快速评估气候政策公众认知，尤其适用于资源有限地区
尽管多数人支持气候行动，但普遍低估他人支持度，阻碍了个体与系统性变革。本预注册实验中，我们测试大语言模型（LLMs）是否能可靠预测全球范围内的这种感知差距。基于125个国家的国家层面指标和盖洛普世界调查2021/22数据，我们对比了四种先进LLM与统计回归模型的表现。结果显示，尤其是Claude模型，在预测公众对他人财政支持意愿方面表现准确（平均绝对误差约5个百分点；相关系数r = .77），与统计模型相当，但在数字连接度较低、人均GDP较低的国家性能下降。受控测试表明，LLMs捕捉到了关键心理机制——社会投射中的系统性低估偏差，并依赖结构化推理而非记忆数值。总体而言，LLMs为快速评估气候行动感知差距提供了高效工具，在资源丰富国家可替代昂贵调查，在代表性不足群体中可作为补充。
原文摘要 · Abstract (English)
Although most people support climate action, widespread underestimation of others' support stalls individual and systemic changes. In this preregistered experiment, we test whether large language models (LLMs) can reliably predict these perception gaps worldwide. Using country-level indicators and public opinion data from 125 countries, we benchmark four state-of-the-art LLMs against Gallup World Poll 2021/22 data and statistical regressions. LLMs, particularly Claude, accurately capture public perceptions of others' willingness to contribute financially to climate action (MAE approximately 5 p.p.; r = .77), comparable to statistical models, though performance declines in less digitally connected, lower-GDP countries. Controlled tests show that LLMs capture the key psychological process - social projection with a systematic downward bias - and rely on structured reasoning rather than memorized values. Overall, LLMs provide a rapid tool for assessing perception gaps in climate action, serving as an alternative to costly surveys in resource-rich countries and as a complement in underrepresented populations.
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。