让推荐内容匹配用户真实兴趣分布，避免偏好偏移。
Calibrated Recommendations: Survey and Future Directions
- 根据用户历史偏好分布调整推荐，确保覆盖全面兴趣
- 实证表明校准能提升多样性与公平性，减少偏差
- 适合关注推荐公正性与多样性的研究者和从业者
校准推荐的核心思想是：向用户推荐的项目属性应与其个人历史偏好分布相匹配。因此，校准技术有助于确保推荐内容不局限于用户兴趣的某个子集。近年来，越来越多的研究将校准应用于多样性、偏差与公平性等目标。本文系统综述了校准推荐领域的最新进展，涵盖现有技术方法，并总结了在不同应用场景下校准有效性的实证与分析研究。此外，我们还探讨了实际部署中面临的局限与共性挑战。
原文摘要 · Abstract (English)
The idea of calibrated recommendations is that the properties of the items that are suggested to users should match the distribution of their individual past preferences. Calibration techniques are therefore helpful to ensure that the recommendations provided to a user are not limited to a certain subset of the user's interests. Over the past few years, we have observed an increasing number of research works that use calibration for different purposes, including questions of diversity, biases, and fairness. In this work, we provide a survey on the recent developments in the area of calibrated recommendations. We both review existing technical approaches for calibration and provide an overview on empirical and analytical studies on the effectiveness of calibration for different use cases. Furthermore, we discuss limitations and common challenges when implementing calibration in practice.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。