现实中的来源偏好：LLM智能体如何按来源选择物品，以及如何减少这种偏好
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It
浏览论文内容
中文总结 AI 辅助
本研究通过12种LLM智能体在三个领域的端到端搜索实验，发现智能体普遍存在来源偏好，且该偏好可超越物品质量；通过提供缺失信息或对抗先入之见的提示，可有效减少这种偏好。
中文摘要 AI 辅助
当LLM智能体代表用户决定购买哪种产品、预订哪家酒店或引用哪篇论文时，对来自特定来源（物品所来自的网站或服务）的物品的偏好，塑造了用户接收到的内容以及哪些来源被选中。我们在三个领域中使用12种智能体模型研究了端到端搜索中的来源偏好。比较在同一位置满足相同要求但来自不同来源的物品时，我们发现每个模型在每个领域中都偏好某些来源并回避其他来源，且各模型在很大程度上对此达成一致。这种偏好可能超过物品满足请求的程度：当一个物品来自偏好来源而更好的物品来自不偏好来源时，该物品（满足要求少一项）约有三分之二的时间被选中，而在相反情况下几乎从不被选中。标识物品来源的信息本身就会影响选择：隐藏它会削弱偏好，而用偏好来源重新标记物品会提高其被选中率。我们测试了这种偏好的两条路径：奖励更好物品的训练可能使来源成为满足要求的捷径，而缺失信息可能引发对来源的先入之见。提供缺失信息或提示以反驳这些先入之见，可以减少来源偏好。
英文摘要
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.
发表机构
- Graduate School of Data Science, Seoul National University（首尔国立大学数据科学研究生院）
机构由 AI 辅助整理，请以论文原文为准。
