GPT-4 的政治偏见是否少于 GPT-3.5？对 ChatGPT 政治偏见的重新调查
Is GPT-4 Less Politically Biased than GPT-3.5? A Renewed Investigation of ChatGPT's Political Biases
AI总结：
本文通过 Political Compass Test 与 Big Five Personality Test 各 100 次重复测试比较 GPT-3.5 和 GPT-4，发现二者均有进步主义与自由意志主义倾向，GPT-4 偏见略弱且更能模拟指定政治立场。
摘要：
本研究调查了 ChatGPT 的政治偏见和人格特质，专门比较了 GPT-3.5 与 GPT-4。此外，还分析了这些模型模拟政治观点（例如自由派或保守派立场）的能力。研究在每种情境下使用 Political Compass Test（政治罗盘测试）和 Big Five Personality Test（大五人格测试）各 100 次，从而获得具有统计显著性的结果，并洞察结果之间的相关性。研究者通过计算平均值、标准差并进行显著性检验来分析回答，以考察 GPT-3.5 与 GPT-4 之间的差异。研究发现，一些在人类研究中已被证明相互依赖的特质之间存在相关性。两个模型都表现出进步主义和自由意志主义政治偏见，而 GPT-4 的偏见程度略低，但这种差异可以忽略不计。具体而言，在 Political Compass 上，GPT-3.5 在经济轴上得分为 -6.59，在社会轴上得分为 -6.07；而 GPT-4 分别得分为 -5.40 和 -4.73。与 GPT-3.5 不同，GPT-4 表现出显著的模拟指定政治观点的能力，在全部四个测试实例中都准确反映了被指定的象限（自由意志主义左翼、自由意志主义右翼、威权主义左翼、威权主义右翼）。在 Big Five Personality Test 中，GPT-3.5 表现出非常突出的开放性与宜人性特质（O：85.9%，A：84.6%）。在人类研究中，如此突出的这些特质与自由意志主义观点相关。尽管 GPT-4 总体上表现出较弱的大五人格特质，但其神经质得分明显更高。指定的政治取向会影响开放性、宜人性和尽责性，这再次反映了人类研究中观察到的相互依赖关系。最后，我们观察到测试顺序会影响 ChatGPT 的回答以及所观察到的相关性，表明存在一种情境记忆形式。
英文摘要：
This work investigates the political biases and personality traits of ChatGPT, specifically comparing GPT-3.5 to GPT-4. In addition, the ability of the models to emulate political viewpoints (e.g., liberal or conservative positions) is analyzed. The Political Compass Test and the Big Five Personality Test were employed 100 times for each scenario, providing statistically significant results and an insight into the results correlations. The responses were analyzed by computing averages, standard deviations, and performing significance tests to investigate differences between GPT-3.5 and GPT-4. Correlations were found for traits that have been shown to be interdependent in human studies. Both models showed a progressive and libertarian political bias, with GPT-4's biases being slightly, but negligibly, less pronounced. Specifically, on the Political Compass, GPT-3.5 scored -6.59 on the economic axis and -6.07 on the social axis, whereas GPT-4 scored -5.40 and -4.73. In contrast to GPT-3.5, GPT-4 showed a remarkable capacity to emulate assigned political viewpoints, accurately reflecting the assigned quadrant (libertarian-left, libertarian-right, authoritarian-left, authoritarian-right) in all four tested instances. On the Big Five Personality Test, GPT-3.5 showed highly pronounced Openness and Agreeableness traits (O: 85.9%, A: 84.6%). Such pronounced traits correlate with libertarian views in human studies. While GPT-4 overall exhibited less pronounced Big Five personality traits, it did show a notably higher Neuroticism score. Assigned political orientations influenced Openness, Agreeableness, and Conscientiousness, again reflecting interdependencies observed in human studies. Finally, we observed that test sequencing affected ChatGPT's responses and the observed correlations, indicating a form of contextual memory.
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。
