The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search
作者: Hana Samad, Trung Lam, Christoph Mügge-Durum, Michael Akinwumi
分类: cs.LG, cs.AI, cs.CY
发布日期: 2026-06-04
备注: 13 pages with supplemental tables and figures, AIES '26 Submission
💡 一句话要点
通过行为审计揭示LLM在住房搜索中的种族引导问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 大型语言模型 住房搜索 种族引导 行为审计 公平住房 用户身份 空间逻辑
📋 核心要点
- 现有方法在住房搜索中存在种族引导现象,导致不同用户在相同偏好下获得不同的推荐结果。
- 本文通过对七个LLM进行行为审计,探索用户身份与模型内化空间逻辑的交互,提出了一种新的测试方法。
- 实验结果显示,偏好条件测试增加了表现出引导行为的模型数量,表明LLMs对相同住房偏好的解读因用户种族身份而异。
📝 摘要(中文)
大型语言模型(LLMs)在住房搜索中迅速扮演中介角色,通过对话界面整合房源平台,调解城市环境中的信息获取、搜索和推荐。本文扩展了关于LLMs中种族引导的研究,针对七个开放权重和闭源LLMs在四个美国城市进行行为审计,测试不同生活方式偏好的位置推荐。研究发现,种族引导是模型解释性许可的涌现行为,而非静态属性,且不同用户的身份和偏好表达与模型内化的空间逻辑相互作用,导致引导行为的方向和强度不均。结果表明,城市并非LLM评估的中立单位,需结合地方和领域专业知识,以确保在采用AI工具时不削弱公平住房的法律和制度承诺。
🔬 方法详解
问题定义:本文旨在解决大型语言模型在住房搜索中可能引发的种族引导问题,现有方法未能充分考虑用户身份与模型推荐之间的关系。
核心思路:通过对七个不同的LLM进行行为审计,结合生活方式偏好上下文,探索模型如何在不同用户身份下表现出不同的推荐行为。
技术框架:研究采用了四个美国城市的房源数据,设计了三种迭代提示条件,逐步增加生活方式偏好信息,使用公平住房配对测试方法进行评估。
关键创新:本研究的创新在于揭示了种族引导是模型解释性许可的涌现行为,而非静态属性,强调了用户身份与模型内化空间逻辑的相互作用。
关键设计:实验中使用了开放权重和闭源LLM,设置了不同的提示条件,采用了公平住房的配对测试方法,确保了实验的有效性和可靠性。
🖼️ 关键图片
📊 实验亮点
实验结果表明,在偏好条件测试下,表现出引导行为的模型数量相较于基线条件显著增加,表明LLMs对相同住房偏好的解读因用户的种族身份而异。这一发现强调了城市作为LLM评估单位的重要性。
🎯 应用场景
该研究的潜在应用领域包括住房搜索平台、房地产推荐系统及相关政策制定。通过理解LLM在不同用户群体中的表现,可以帮助开发更公平的AI工具,确保在住房领域的公平性和合规性,促进社会正义。
📄 摘要(原文)
Large language models (LLMs) are rapidly assuming an intermediary role in housing search through the integration of listing platforms within conversational interfaces, mediating access to information, search, and recommendations within urban settings. We expand on prior work on racial steering in LLMs by conducting a behavioral audit of seven open-weight and closed-source LLMs across four U.S. cities, testing location recommendations across three iterative prompting conditions that progressively add lifestyle preference context and reflect fair housing paired-testing methodologies. We find that steering is an emergent behavior of the model's interpretive license rather than primarily a static property. Steering results from the interaction of a user's identity, preference articulation, and the spatial logic that a model has internalized about learned representations of place, preference, and opportunity in a given city, and how different types of users relate to it. While steering was present, it was not uniform in direction or magnitude across evaluated conditions. Preference-conditioned testing often increased or reconfigured the number of models that exhibited steering behaviors relative to baseline conditions, suggesting that LLMs may interpret what the same housing preference means differently depending on the racial identity of the user. Our findings also demonstrate that the city is not a neutral testing unit for LLM evaluation in place-based sectors, and results from one local market cannot be assumed to generalize to another. Local and domain expertise will be required in the housing sector to ensure that legal and institutional commitments to fair housing are not undermined while adopting AI tools that mediate spatial access.