LLM推荐文献时偏好男性作者，且倾向多数性别，可能加剧学术不公。
Who Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection
- 用匿名作者名控制实验，测试LLM选参考文献的性别倾向。
- 男性作者更易被选中，且多数性别优势明显，大样本下更严重。
- 社科领域偏差最小，提示词缓解有限，需更强干预策略。
大型语言模型（LLMs）正被广泛用于科研辅助，尤其是文献综述与参考文献推荐，但其是否引入人口统计学偏见尚不清楚。本研究通过控制实验，使用伪匿名作者名系统性地考察了LLM在参考文献选择中的性别偏见。我们评估了GPT-4o、GPT-4o-mini、Claude Sonnet和Claude Haiku等多个LLM，在不同性别构成的候选文献池中分析其选择模式。结果揭示两种偏见：持续偏好男性作者，以及多数群体偏见——即更倾向于选择候选池中占多数的性别。这种偏见在更大候选池中加剧，且仅通过提示词进行的缓解措施效果有限。领域级分析显示，偏见程度在各科学领域中存在差异，社会科学中的偏见最小。研究表明，LLM可能强化甚至放大现有学术认可中的性别失衡。为避免在高风险学术流程中延续性别不平等，亟需有效的缓解策略。
原文摘要 · Abstract (English)
Large language models (LLMs) are rapidly being adopted as research assistants, particularly for literature review and reference recommendation, yet little is known about whether they introduce demographic bias into citation workflows. This study systematically investigates gender bias in LLM-driven reference selection using controlled experiments with pseudonymous author names. We evaluate several LLMs (GPT-4o, GPT-4o-mini, Claude Sonnet, and Claude Haiku) by varying gender composition within candidate reference pools and analyzing selection patterns across fields. Our results reveal two forms of bias: a persistent preference for male-authored references and a majority-group bias that favors whichever gender is more prevalent in the candidate pool. These biases are amplified in larger candidate pools and only modestly attenuated by prompt-based mitigation strategies. Field-level analysis indicates that bias magnitude varies across scientific domains, with social sciences showing the least bias. Our findings indicate that LLMs can reinforce or exacerbate existing gender imbalances in scholarly recognition. Effective mitigation strategies are needed to avoid perpetuating existing gender disparities in scientific citation practices before integrating LLMs into high-stakes academic workflows.
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。