arXiv:2507.07919cs.LGcs.IR2025-07

提出生成更可信推荐反事实解释的方法,提升可解释性。

Plausible Counterfactual Explanations of Recommendations

  • 基于用户行为生成高可信度反事实解释
  • 数值评估与用户研究验证有效性
  • 适合关注推荐系统可解释性的研究者

解释在各类推荐系统中扮演多种角色,从法律要求的补充说明,到用户体验的核心部分,再到提升说服力的关键。一种自然且有用的解释形式是反事实解释(Counterfactual Explanation, CE)。本文提出一种在推荐系统中生成高度可信反事实解释的方法,并通过数值实验和用户研究进行了评估。

原文摘要 · Abstract (English)

Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study.

推荐系统反事实解释可解释性

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。