大型语言模型如何系统性地歪曲美国气候观点
How Large Language Models Misrepresent American Climate Opinions
AI总结:
本文研究了大型语言模型在分析美国气候观点时对交集身份的代表性问题,发现模型压缩了观点多样性,可能影响气候治理公平性。
摘要:
联邦机构和研究人员越来越多地使用大型语言模型来分析和模拟公众意见。当人工智能在公众与政策制定者之间起中介作用时,交叉身份的准确性变得至关重要;不准确的群体层面估计可能导致误导性沟通、咨询和政策设计。尽管已有研究探讨了LLM输出中的交集性,但很少有研究将这些输出与真实的人类响应在交叉身份上进行比较。气候政策是一个这样的领域,特别是在气候变化问题上,意见存在争议且多样。我们研究了LLM在表示美国气候观点的种族和交集性模式时的表现。我们提示了六个LLM,使用来自全国代表性美国气候观点调查的978名受访者资料,并将AI生成的响应与实际人类答案在20个问题上进行比较。我们发现,LLM似乎压缩了美国气候观点的多样性,预测较少关注的群体更关注,反之亦然。这种压缩是交集性的:LLM似乎应用了与现实相符的性别假设,适用于白人和拉丁美洲人,但可能歪曲了黑人的性别模式,因为实际性别模式不同。这些模式,可能对标准审计方法来说是不可见的,可能会影响公平的气候治理。
英文摘要:
Large language models are increasingly used to simulate public opinion, standing in for survey respondents as "silicon samples." Whether they faithfully represent U.S. climate opinion, particularly at the intersections of race, gender, and ideology, remains largely untested. We prompted six large language models with the profiles of 978 respondents to a nationally representative U.S. climate opinion survey and compared the generated responses with those respondents' own answers across 20 questions. The models compress the diversity of American climate opinion, pulling predictions toward the population mean: less-concerned groups are predicted as more concerned, more-concerned groups as less, and the variance of predicted responses falls, on average, 29% below that of human responses. The compression is intersectional. The models apply one gender assumption, predicting women as more pro-climate than men in every racial group. The assumption matches the direction of the human pattern for White, Hispanic, and Other Americans and runs the wrong way for Black Americans. We claim the direction of that difference rather than its size, since it rests on small cells at the ideological extreme. An audit of gender alone would report that the models understate the gender gap, and would miss that the error changes direction by race, which is what single-variable audits cannot detect. What is at stake is not accuracy alone but representation: whose views a synthetic sample renders legible.
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。