研究大模型在亲密关系决策中的性别偏见，发现模型倾向女性和中性名者。
Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts
- 构建新数据集DeMET Prompts，测试九种关系场景下的性别角色偏见。
- 所有模型均显示女性优先、男性最弱，安全机制可降低偏见。
- 模型更支持传统女性角色，暗示其将亲密关系视为女性主导领域。
大型语言模型（LLMs）从训练数据中习得性别观念，可能生成带有刻板印象的文本。以往研究已揭示模型对特定性别的偏好或性别刻板印象，但未深入探讨影响模型推理与决策的复杂动态。本文通过新构建的数据集DeMET Prompts，以亲密恋爱关系为场景，考察模型中的性别公平性。研究涵盖三类姓名列表（男性、女性、中性名），组合成九种关系配置，从多个维度分析：典型与中性姓名、有无安全防护、同性与异性关系、平等与传统情境等。结果显示，所有模型均表现出一致偏见：女性被优先，其次为中性名者，最后是男性；安全防护措施能有效缓解偏见。此外，模型倾向于规避传统男性主导叙事，更常支持‘传统上属于女性’的角色，表明模型将亲密关系视为女性主导领域。
原文摘要 · Abstract (English)
Large language models (LLMs) acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. Prior studies have demonstrated model generations favor one gender or exhibit stereotypes about gender, but have not investigated the complex dynamics that can influence model reasoning and decision-making involving gender. We study gender equity within LLMs through a decision-making lens with a new dataset, DeMET Prompts, containing scenarios related to intimate, romantic relationships. We explore nine relationship configurations through name pairs across three name lists (men, women, neutral). We investigate equity in the context of gender roles through numerous lenses: typical and gender-neutral names, with and without model safety enhancements, same and mixed-gender relationships, and egalitarian versus traditional scenarios across various topics. While all models exhibit the same biases (women favored, then those with gender-neutral names, and lastly men), safety guardrails reduce bias. In addition, models tend to circumvent traditional male dominance stereotypes and side with 'traditionally female' individuals more often, suggesting relationships are viewed as a female domain by the models.
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。