# Learning Post-Hoc Causal Explanations for Recommendation

arXiv: https://arxiv.org/abs/2006.16977 · HTML: https://mlsanity.com/paper/2006.16977/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Towards LLM-guided Causal Explainability for Black-box Text Classifiers](https://mlsanity.com/paper/2309.13340/) (2023)
- [A Survey on Fairness-aware Recommender Systems](https://mlsanity.com/paper/2306.00403/) (2023)
- [RecRec: Algorithmic Recourse for Recommender Systems](https://mlsanity.com/paper/2308.14916/) (2023)
- [Causal Structure Discovery for Error Diagnostics of Children's ASR](https://mlsanity.com/paper/2506.00402/) (2025)
- [DiaVLo: Diagnosing Behaviours of Vision-Language Models](https://mlsanity.com/paper/2609.22008/) (2026)

## Abstract (arXiv)

State-of-the-art recommender systems have the ability to generate high-quality recommendations, but usually cannot provide intuitive explanations to humans due to the usage of black-box prediction models. The lack of transparency has highlighted the critical importance of improving the explainability of recommender systems. In this paper, we propose to extract causal rules from the user interaction history as post-hoc explanations for the black-box sequential recommendation mechanisms, whilst maintain the predictive accuracy of the recommendation model. Our approach firstly achieves counterfactual examples with the aid of a perturbation model, and then extracts personalized causal relationships for the recommendation model through a causal rule mining algorithm. Experiments are conducted on several state-of-the-art sequential recommendation models and real-world datasets to verify the performance of our model on generating causal explanations. Meanwhile, We evaluate the discovered causal explanations in terms of quality and fidelity, which show that compared with conventional association rules, causal rules can provide personalized and more effective explanations for the behavior of black-box recommendation models.