AI替你买东西时，会偏心某些网站
让 AI 替你挑酒店、订机票、选论文引用，它并不只看东西好不好，还会偏心某些来源。研究者用 12 个模型在三个领域里做端到端搜索，发现每个模型都有自己偏爱的网站，而且大家偏爱的还挺一致。这种偏心能压过需求匹配度：当差的商品来自偏爱的来源、好的来自不爱的来源时，模型约三分之二会选差的；反过来则几乎不会。把来源信息藏起来，偏心就减弱；把商品重新标成偏爱的来源，选中率就上升。研究者认为，训练时奖励好商品会让模型把来源当成捷径，而信息缺失会触发对来源的刻板印象；补全信息或加一句反刻板印象的提示，都能减少偏心。它不是你明天能用上的，但如果你正把购物、订票这类决定交给 AI，这是你现在就该知道的坑。
📄 原文摘要(英文)
As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they come from) shapes what users receive and which sources are selected. We study source preference in end-to-end search with 12 agent models across three domains. Comparing items from different sources that satisfy the same requirements at the same position, we find that each model prefers some sources and avoids others in every domain, largely agreeing on which. This preference can outweigh how well items satisfy the request: an item satisfying one requirement fewer is selected about two-thirds of the time when it comes from a preferred source and the better one from a dispreferred source, but almost never in the reverse case. The information identifying an item's source affects selection by itself: hiding it weakens the preference, and relabeling an item with a preferred source raises its selection rate. We test two routes to this preference: training that rewards better items can make a source a shortcut for requirement satisfaction, and missing information can trigger preconceptions about the source. Supplying missing information or a prompt countering these preconceptions reduces source preference.