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.

翻译：旅行者越来越依赖大语言模型（LLM）助手的建议来决定预订哪家酒店，这使得这些系统成为酒店可见性的守门人——然而，驱动其推荐的因素尚未得到系统记录。我们开展了一项预先指定的算法审计，采用基于随机选择的联合分析方法：在不同的用户画像、提示模板以及十二个开源和专有模型中，助手需从五家酒店中进行选择，这些酒店的住客评分、评论数量与时效性、管理回复、连锁品牌、价格、生态认证以及列表位置均经过独立随机化处理。我们估算了每个信号对推荐概率的平均边际成分效应。住客评分和价格占据主导地位（最高评分使选择率提升31.6个百分点，高价格则使选择率降低30.0个百分点），这重现了人类评价-价格优先的决策模式，但系统高估了生态认证的作用，且完全忽略管理回复。列表位置——一个无内容的伪特征——对推荐产生因果性影响，其效应相当于每晚约12美元的价格差异。系统明确陈述的理由与隐含权重之间存在不完全匹配。研究结果为生成式引擎优化及AI信息中介的责任机制提供了因果性实证依据。