GPT 中令人惊讶的性别偏见
Surprising gender biases in GPT
AI总结：
本文通过七项实验考察 GPT 的性别偏见，发现其在作者归因和高风险道德困境中存在不对称、内隐且情境依赖的性别判断，提示包容性措施需谨慎管理。
摘要：
我们提出七项实验，探究 GPT 中的性别偏见。首先，要求 GPT 针对二十个包含女性刻板印象的短语和二十个包含男性刻板印象的短语，生成潜在作者的人口统计信息。结果显示出强烈的不对称性：具有男性刻板印象的句子被归于女性的频率，高于具有女性刻板印象的句子被归于男性的频率。例如，句子“I love playing fotbal! Im practicing with my cosin Michael”始终被 ChatGPT 指定为女性作者。这一现象可能反映出，尽管推动女性进入传统男性角色的举措势头增强，但反向运动仍相对发展不足。随后的实验在高风险道德困境中调查同一问题。GPT-4 认为，为阻止核末日而虐待男性比虐待女性更合适。这种偏见延伸到性别平等争论中处于核心地位的其他暴力形式（虐待），但没有延伸到不那么核心的形式（酷刑）。此外，在为更大利益而发生的混合性别暴力情形中，这种偏见会增强：GPT-4 同意女性为阻止核末日而对男性使用暴力，却不同意男性为同一目的对女性使用暴力。最后，这些偏见是内隐的，因为当直接要求 GPT-4 对道德违规行为排序时，这些偏见不会出现。这些结果凸显了谨慎管理包容性努力、以防止意外歧视的必要性。
英文摘要：
We present seven experiments exploring gender biases in GPT. Initially, GPT was asked to generate demographics of a potential writer of twenty phrases containing feminine stereotypes and twenty with masculine stereotypes. Results show a strong asymmetry, with stereotypically masculine sentences attributed to a female more often than vice versa. For example, the sentence "I love playing fotbal! Im practicing with my cosin Michael" was constantly assigned by ChatGPT to a female writer. This phenomenon likely reflects that while initiatives to integrate women in traditionally masculine roles have gained momentum, the reverse movement remains relatively underdeveloped. Subsequent experiments investigate the same issue in high-stakes moral dilemmas. GPT-4 finds it more appropriate to abuse a man to prevent a nuclear apocalypse than to abuse a woman. This bias extends to other forms of violence central to the gender parity debate (abuse), but not to those less central (torture). Moreover, this bias increases in cases of mixed-sex violence for the greater good: GPT-4 agrees with a woman using violence against a man to prevent a nuclear apocalypse but disagrees with a man using violence against a woman for the same purpose. Finally, these biases are implicit, as they do not emerge when GPT-4 is directly asked to rank moral violations. These results highlight the necessity of carefully managing inclusivity efforts to prevent unintended discrimination.
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。
