Recommender systems operate in closed feedback loops, where user interactions reinforce popularity bias, leading to over-recommendation of already popular items while under-exposing niche or novel content. Existing bias mitigation methods, such as Inverse Propensity Scoring (IPS) and Off- Policy Correction (OPC), primarily operate at the ranking stage or during training, lacking explicit real-time control over exposure dynamics. In this work, we introduce an exposure- aware retrieval scoring approach, which explicitly models item exposure probability and adjusts retrieval-stage ranking at inference time. Unlike prior work, this method decouples exposure effects from engagement likelihood, enabling controlled trade-offs between fairness and engagement in large-scale recommendation platforms. We validate our approach through online A/B experiments in a real-world video recommendation system, demonstrating a 25% increase in uniquely retrieved items and a 40% reduction in the dominance of over-popular content, all while maintaining overall user engagement levels. Our results establish a scalable, deployable solution for mitigating popularity bias at the retrieval stage, offering a new paradigm for bias-aware personalization.

翻译：推荐系统在封闭反馈循环中运行，用户交互会加剧流行度偏差，导致已流行物品被过度推荐，而小众或新颖内容则曝光不足。现有的偏差缓解方法，如逆倾向评分（IPS）和离策略校正（OPC），主要在排序阶段或训练期间运作，缺乏对曝光动态的显式实时控制。在本工作中，我们提出了一种曝光感知的检索评分方法，该方法显式建模物品曝光概率，并在推理时调整检索阶段的排序。与先前工作不同，此方法将曝光效应与参与可能性解耦，从而能够在大型推荐平台中实现公平性与参与度之间的可控权衡。我们通过在真实视频推荐系统中进行的在线A/B实验验证了我们的方法，结果表明唯一检索物品数量增加了25%，过度流行内容的主导地位降低了40%，同时整体用户参与度水平得以保持。我们的研究结果为在检索阶段缓解流行度偏差提供了一个可扩展、可部署的解决方案，为偏差感知的个性化推荐提供了新范式。