为上下文猜拳系统设计可解释界面，让非专家也能理解模型决策。
Designing an Interpretable Interface for Contextual Bandits
- 用离线评估的'价值增益'指标量化模型各部分的实际影响。
- 用户研究显示界面能帮助非专家有效管理复杂推荐系统。
- 适合想提升推荐系统透明度的研究者与产品经理。
上下文猜拳算法在个性化推荐系统中应用日益广泛，但其可解释性仍是重大挑战，尤其对缺乏机器学习背景的运营人员而言。本文提出一种新界面，通过引入基于离线评估的“价值增益”指标，量化推荐系统中各子组件的真实世界影响，以解释算法行为。我们开展定性用户研究，结果表明：在技术严谨性与展示易懂性之间取得平衡，可使非专家有效参与复杂机器学习系统的管理。最后，我们总结出未来构建类似接口时应遵循的指导原则。
原文摘要 · Abstract (English)
Contextual bandits have become an increasingly popular solution for personalized recommender systems. Despite their growing use, the interpretability of these systems remains a significant challenge, particularly for the often non-expert operators tasked with ensuring their optimal performance. In this paper, we address this challenge by designing a new interface to explain to domain experts the underlying behaviour of a bandit. Central is a metric we term "value gain", a measure derived from off-policy evaluation to quantify the real-world impact of sub-components within a bandit. We conduct a qualitative user study to evaluate the effectiveness of our interface. Our findings suggest that by carefully balancing technical rigour with accessible presentation, it is possible to empower non-experts to manage complex machine learning systems. We conclude by outlining guiding principles that other researchers should consider when building similar such interfaces in future.
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。