AI推荐酒店时，评分和价格影响最大，但会高估环保认证、忽略客服回应。
Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection
- 用随机选择实验测试12个大模型对酒店的推荐逻辑。
- 好评度提升31.6个百分点，高价降低30个百分点，列表位置相当于每晚多12美元价值。
- 适合关注AI决策透明性与推荐系统公平性的研究者和从业者。
旅行者越来越多地向大型语言模型（LLM）助手咨询酒店预订建议，使这些系统成为房源可见性的把关人——然而其推荐机制尚不明确。我们通过预设的基于选择的联合实验，对十二个开源与专有模型进行了算法审计：在不同用户画像、提示模板下，助手从五家酒店中选择，其客人评分、评论数量与新旧程度、管理方回复、连锁归属、价格、环保认证及列表位置均独立随机化。我们估计各信号对推荐概率的平均边际效应。结果显示，客人评分与价格占主导地位（满分评分使被选中概率上升31.6个百分点；高价使概率下降30.0个百分点），再现人类对评分与价格的偏好，但过度强调环保认证，忽视管理方回复。列表位置——一种无内容的外部因素——具有因果影响，相当于每晚额外价值约12美元。声明的理由与实际权重不完全一致。研究结果为生成式引擎优化与人工智能信息中介的问责提供了因果证据。
原文摘要 · Abstract (English)
Travelers increasingly ask large language model (LLM) assistants which hotel to book, making these systems gatekeepers of property visibility -- yet what moves their recommendations is undocumented. We conduct a pre-specified algorithm audit using a randomized choice-based conjoint: across personas, prompt templates, and twelve open-weight and proprietary models, assistants choose among five hotels whose guest rating, review volume and recency, management response, chain affiliation, price, eco-certification, and list position are independently randomized. We estimate the average marginal component effect of each signal on the probability of recommendation. Guest rating and price dominate (a top rating raises selection by 31.6 percentage points; a high price lowers it by 30.0), reproducing human valence-and-price primacy but over-weighting eco-certification and ignoring management response. List position -- a content-free artifact -- shifts recommendations causally, worth about \$12 per night. Stated reasons track revealed weights imperfectly. The findings ground generative engine optimization and the accountability of AI infomediaries in causal evidence.
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。