Keywords
recommendation explanations
domain shift
explanation faithfulness
counterfactual learning
evaluation
Abstract
What evidence is needed to determine whether counterfactual domain data can reduce generic and repetitive recommendation explanations? This review answers by treating domain-counterfactual explanation learning as a property of a sociotechnical workflow rather than a feature that can be read from average accuracy. The focal setting is explainable recommendation where generic language may mask weak dependence on the recommended item, where behavioral traces are selective and explanations can be persuasive without being faithful to the decision process. Evidence from the assigned publications is synthesized with foundational studies of calibration, distribution shift, causal structure, and responsible deployment. Four requirements follow: preserve the lineage of discussion text, interaction sequences, item attributes, explanation pools, temporal context, and user feedback; measure stability across relevant perturbations; connect confidence to a specific action; and maintain a route for human challenge and correction. The framework distinguishes descriptive performance from decision utility and separates uncertainty about the world from uncertainty created by the model and its evaluator. It also shows why faster inference or richer reasoning is valuable only when it improves a defined decision under a transparent resource budget. The article is a literature review and research agenda, not a report of a newly completed trial.
References
Yu, Yi, et al. “Domain Counterfactual Data Augmentation for Explainable Recommendation.” ACM Transactions on Information Systems, vol. 43, no. 3, 2025, https://doi.org/10.1145/3711856.
Deng, Huilin, et al. “IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck.” arXiv, version 1, 9 Jan. 2026, https://arxiv.org/abs/2601.05870v1. Preprint.
Siemens, George, and Ryan S. J. d. Baker. “Learning Analytics and Educational Data Mining: Towards Communication and Collaboration.” Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, 2012, pp. 252–54.
Kizilcec, René F., Chris Piech, and Emily Schneider. “Deconstructing Disengagement: Analyzing Learner Subpopulations in Massive Open Online Courses.” Proceedings of the Third International Conference on Learning Analytics and Knowledge, 2013, pp. 170–79.
Rosé, Carolyn Penstein, et al. “Social Factors That Contribute to Attrition in MOOCs.” Proceedings of the First ACM Conference on Learning at Scale, 2014, pp. 197–98.
Blei, David M., Andrew Y. Ng, and Michael I. Jordan. “Latent Dirichlet Allocation.” Journal of Machine Learning Research, vol. 3, 2003, pp. 993–1022.
Rabiner, Lawrence R. “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition.” Proceedings of the IEEE, vol. 77, no. 2, 1989, pp. 257–86.
Hidasi, Balázs, et al. “Session-Based Recommendations with Recurrent Neural Networks.” International Conference on Learning Representations, 2016.
Kang, Wang-Cheng, and Julian McAuley. “Self-Attentive Sequential Recommendation.” 2018 IEEE International Conference on Data Mining, 2018, pp. 197–206.
Zhang, Yongfeng, and Xu Chen. “Explainable Recommendation: A Survey and New Perspectives.” Foundations and Trends in Information Retrieval, vol. 14, no. 1, 2020, pp. 1–101.
Pearl, Judea. Causality: Models, Reasoning, and Inference. 2nd ed., Cambridge University Press, 2009.
Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. “Why Should I Trust You?: Explaining the Predictions of Any Classifier.” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–44.