English(EN) Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection

AI酒店推荐偏重评分和价格，忽略管理方回应

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-15 07:47

arXiv上发表的一项新研究审计了大型语言模型（LLM）在酒店选择中使用的推荐信号。研究发现，与人类偏好类似，住客评分和价格是影响最大的因素，而生态认证等其他信号被过度重视，管理方的回应则被忽略。值得注意的是，酒店在列表中的位置（一个不包含内容的伪影）显著影响了推荐结果，这表明AI信息中介需要优化和问责。 AI

影响强调了在LLM驱动的推荐系统中提高透明度和优化性能的必要性，尤其是在旅游等面向消费者的应用中。

排序理由在arXiv上发表的研究论文，详细介绍了对LLM推荐信号的算法审计。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Asher Ali · 2026-06-16 04:00

Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection

arXiv:2606.16344v1 Announce Type: new Abstract: 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 algori…
arXiv cs.CL TIER_1 English(EN) · Asher Ali · 2026-06-15 07:47

Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection

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 conjoi…

报道来源 [2]

Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection

Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection

相关实体

相关话题