Plausible Counterfactual Explanations of Recommendations

• URL: http://arxiv.org/abs/2507.07919v1
• Date: Thu, 10 Jul 2025 16:59:51 GMT
• Title: Plausible Counterfactual Explanations of Recommendations
• Authors: Jakub Černý, Jiří Němeček, Ivan Dovica, Jakub Mareček,
• Abstract summary: Explanations play a variety of roles in recommender systems.<n>A natural and useful form of an explanation is the Counterfactual Explanation.<n>We present a method for generating highly plausible CEs in recommender systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations [63.05026345443155]
  We propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS's explanations during persuasion. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive and credible explanations. Further analysis reveals the reason behind current methods producing incredible explanations and the potential of credible explanations to improve recommendation accuracy.
  arXiv  Detail & Related papers  (2024-09-22T11:35:59Z)
• Stability of Explainable Recommendation [10.186029242664931]
  We study the vulnerability of existent feature-oriented explainable recommenders. We observe that all the explainable models are vulnerable to increased noise levels. Our study presents an empirical verification on the topic of robust explanations in recommender systems.
  arXiv  Detail & Related papers  (2024-05-03T04:44:51Z)
• User-Controllable Recommendation via Counterfactual Retrospective and Prospective Explanations [96.45414741693119]
  We present a user-controllable recommender system that seamlessly integrates explainability and controllability. By providing both retrospective and prospective explanations through counterfactual reasoning, users can customize their control over the system.
  arXiv  Detail & Related papers  (2023-08-02T01:13:36Z)
• Visualization for Recommendation Explainability: A Survey and New Perspectives [0.0]
  We systematically review the literature on explanations in recommender systems based on four dimensions. We derive a set of guidelines that might be constructive for designing explanatory visualizations in recommender systems. The aim of this review is to help recommendation researchers and practitioners better understand the potential of visually explainable recommendation research.
  arXiv  Detail & Related papers  (2023-05-19T15:42:00Z)
• Explainable Recommender with Geometric Information Bottleneck [25.703872435370585]
  We propose to incorporate a geometric prior learnt from user-item interactions into a variational network. Latent factors from an individual user-item pair can be used for both recommendation and explanation generation. Experimental results on three e-commerce datasets show that our model significantly improves the interpretability of a variational recommender.
  arXiv  Detail & Related papers  (2023-05-09T10:38:36Z)
• RecXplainer: Amortized Attribute-based Personalized Explanations for Recommender Systems [35.57265154621778]
  We propose RecXplainer, a novel method for generating fine-grained explanations based on a user's preferences over the attributes of recommended items. We evaluate RecXplainer on five real-world and large-scale recommendation datasets.
  arXiv  Detail & Related papers  (2022-11-27T21:00:31Z)
• Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation [87.82664566721917]
  This survey is based on more than 100 papers from top-tier conferences like IJCAI, AAAI, TheWebConf, Recsys, UMAP, and IUI.
  arXiv  Detail & Related papers  (2022-02-14T02:58:55Z)
• Counterfactual Explainable Recommendation [22.590877963169103]
  We propose Counterfactual Explainable Recommendation (CountER), which takes the insights of counterfactual reasoning from causal inference for explainable recommendation. CountER seeks simple (low complexity) and effective (high strength) explanations for the model decision. Results show that our model generates more accurate and effective explanations than state-of-the-art explainable recommendation models.
  arXiv  Detail & Related papers  (2021-08-24T06:37:57Z)
• Designing Explanations for Group Recommender Systems [0.0]
  Explanations are used in recommender systems for various reasons. Developers of recommender systems want to convince users to purchase specific items. Users should better understand how the recommender system works and why a specific item has been recommended.
  arXiv  Detail & Related papers  (2021-02-24T17:05:39Z)
• Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect [89.91745908462417]
  We show the benefits of pre-training to recommender systems through experiments. We discuss several promising directions for future research for recommender systems with pre-training.
  arXiv  Detail & Related papers  (2020-09-19T13:06:27Z)
• Sequential Recommendation with Self-Attentive Multi-Adversarial Network [101.25533520688654]
  We present a Multi-Factor Generative Adversarial Network (MFGAN) for explicitly modeling the effect of context information on sequential recommendation. Our framework is flexible to incorporate multiple kinds of factor information, and is able to trace how each factor contributes to the recommendation decision over time.
  arXiv  Detail & Related papers  (2020-05-21T12:28:59Z)
• Survey for Trust-aware Recommender Systems: A Deep Learning Perspective [48.2733163413522]
  It becomes critical to embrace a trustworthy recommender system. This survey provides a systemic summary of three categories of trust-aware recommender systems.
  arXiv  Detail & Related papers  (2020-04-08T02:11:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.