AI写作助手会把性别偏见传给学生，让女生职业描述更被动。
Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing
- 用带偏见的提示词诱导AI生成不同性别的职业描述。
- 受偏见AI辅助的学生，女性目标文章中主动性降低37%。
- 适合教育AI设计者和关注公平性的研究者参考。
大型语言模型中的性别偏见已被广泛研究，已有证据表明，带有偏见的提示词会放大刻板印象输出。然而，这种偏见是否会传递到使用这些系统的学生产出文本中，仍缺乏深入探讨。我们研究了在学生撰写职业规划论文时，语言模型写作助手中的性别偏见是否会发生转移。首先，我们验证了带有性别偏见的提示词会导致模型生成具有性别差异的语言，而中性提示则不会。随后，在受控环境中招募123名参与者，为仅性别不同的成对人物传记撰写职业规划论文，共三种条件：无AI协助、中性AI协助、带偏见的AI协助。结果显示，接受偏见型AI协助的学生所撰写的女性目标文章，其主动性差距显著更大，且更倾向于推荐性别刻板的职业选择；而男性目标文章基本不受影响。该偏见传递具有不对称性：女性相关文本的主动性被抑制，男性相关文本未见明显变化。研究揭示了教育类AI工具中偏见传播的风险，呼吁在设计中引入公平性考量。
原文摘要 · Abstract (English)
Gender bias in LLMs has been studied extensively in model outputs, with biased prompts shown to amplify stereotyped generations. Whether such bias propagates into text produced by humans who use these systems, however, remains underexplored. We investigate whether gender bias in an LLM writing assistant transfers into career plan essays written by students. We first verify that a gender-biased prompt induces gender-differentiated language in LLM-generated essays, while a neutral prompt does not. We then recruited participants (N = 123) in a controlled environment to write career plan essays for paired biographical profiles differing only in gender under three conditions: no AI assistance, neutral LLM assistance, or gender-biased LLM assistance. Students in the biased condition produced essays with a significantly larger agentic gap and more gender-stereotypic occupation suggestions than those in the control and neutral conditions. Our results also reveal that this bias transfer is asymmetric: agency is suppressed in female-target essays while male-target writing remains largely unaffected. Our findings highlight the risk of bias propagation in AI-assisted writing, calling for fairness-aware design in educational AI tools.
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。