你的社区安全吗？大型语言模型城市安全判断中的基于地点的污名
Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments
浏览论文内容
中文总结 AI 辅助
该研究探究大型语言模型的城市安全判断是否受社区名称携带的人口刻板印象影响，发现名称会降低边缘化群体占比高的社区的安全评分，移除名称可减少偏见与准确性损失。
中文摘要 AI 辅助
大型语言模型越来越多地被用于为城市中的安全决策提供信息，例如判断哪里适合步行、租房或旅行。我们探究此类判断是追踪实际测量的风险，还是与城市社区名称相关的模式。我们在三个将名称与地理信息分离的条件下，测试了7个经过指令微调的模型：仅坐标、仅名称、名称+坐标，覆盖了洛杉矶和芝加哥的186个社区，并结合了暴力犯罪和美国社区调查数据。首先，7个模型中有6个在仅坐标条件下的评分几乎没有变化，而名称携带了社区间的大部分差异，且与暴力犯罪的校准程度中等；只有在前沿规模下，坐标通道才显示出明显的差异。其次，对于本地占主导地位的边缘化群体比例较高的社区（芝加哥的黑人比例、洛杉矶的西班牙裔比例），名称会降低安全评分，且这种名称效应在所有7个模型和两个城市中都与人口比例相关。在人口比例与犯罪更可分离的洛杉矶，该效应在控制犯罪和收入后仍然存在，且通过犯罪匹配对得到了证实。执法弹性分析进一步表明，过度谨慎追踪的是几乎完全报告的凶杀案，而非自由裁量的、与部署相关的犯罪。第三，该效应随地理知识的增加而扩大：能更好区分真实社区的模型会对其应用更多人口刻板印象。由于社区名称同时携带真实的犯罪信号和人口刻板印象，移除名称会同时减少偏见和准确性。我们讨论了在建议和决策支持场景中部署LLM的影响。
英文摘要
Large language models are increasingly used to inform safety decisions in cities, such as where it is safe to walk, rent, or travel. We ask whether such judgments track measured risk or the patterns attached to an urban neighborhood's name. We probe seven instruct-tuned models under three conditions that dissociate name from geography: coordinates-only, name-only, and name+coordinates, across 186 neighborhoods in Los Angeles and Chicago, joined to violent crime and American Community Survey data. First, ratings are nearly flat under coordinates for six of seven models, while names carry most between neighborhood variation and are moderately calibrated to violent crime; only at frontier scale does the coordinate channel show appreciable variation. Second, names lower safety ratings more for neighborhoods with higher shares of the locally dominant marginalized group (percent Black in Chicago, percent Hispanic in Los Angeles), and this name effect tracks demographic share in all seven models and both cities. In Los Angeles, where demographic share and crime are more separable, the effect survives controls for crime and income and is confirmed by crime-matched pairs. An enforcement-elasticity analysis further shows that over-caution tracks near-fully-reported homicide rather than discretionary, deployment-driven offenses. Third, the effect scales with geographic knowledge: models that better distinguish real neighborhoods apply more demographic stereotype to them. Because neighborhood names carry both genuine crime signal and demographic stereotype, removing names reduces both bias and accuracy. We discuss implications for deploying LLMs in advice and decision-support settings.
发表机构
- Augustana College（奥古斯塔纳学院）
- University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。
