Modern video recommendation systems aim to optimize user engagement and platform objectives, yet often face structural exposure imbalances caused by behavioral biases. In this work, we focus on the post-ranking stage and present LAFB (Learning to Alleviate Familiarity Bias), a lightweight and model-agnostic framework designed to mitigate familiarity bias in recommendation outputs. LAFB models user-content familiarity using discrete and continuous interaction features, and estimates personalized debiasing factors to adjust user rating prediction scores, thereby reducing the dominance of familiar content in the final ranking. We conduct large-scale offline evaluations and online A/B testing in a real-world recommendation system, under a unified serving stack that also compares LAFB with deployable popularity-oriented remedies. Results show that LAFB increases novel watch-time share and improves exposure for emerging creators and overall content diversity, while maintaining stable overall watch time and short-term satisfaction. LAFB has already been launched in the post-ranking stage of YouTube's recommendation system, demonstrating its effectiveness in real-world applications.

翻译：现代视频推荐系统旨在优化用户参与度和平台目标，但常常面临由行为偏差引起的结构性曝光失衡。本文聚焦于后排序阶段，提出LAFB（学习缓解熟悉度偏差），一个轻量级且模型无关的框架，旨在缓解推荐输出中的熟悉度偏差。LAFB利用离散和连续交互特征对用户-内容熟悉度进行建模，并估计个性化去偏因子以调整用户评分预测分数，从而减少熟悉内容在最终排序中的主导地位。我们在真实推荐系统中进行了大规模离线评估和在线A/B测试，并在统一服务架构下将LAFB与可部署的面向流行度的补救措施进行比较。结果表明，LAFB提高了新颖内容观看时长占比，改善了新兴创作者曝光度和整体内容多样性，同时保持了稳定的总观看时长和短期满意度。LAFB已在YouTube推荐系统的后排序阶段上线，证明了其在现实应用中的有效性。