# Explanation as a Defense of Recommendation

arXiv: https://arxiv.org/abs/2101.09656 · HTML: https://mlsanity.com/paper/2101.09656/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 24 Jan 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Neural Rating Regression with Abstractive Tips Generation for Recommendation](https://mlsanity.com/paper/1708.00154/) (2017)
- [Explainable Recommendation via Multi-Task Learning in Opinionated Text Data](https://mlsanity.com/paper/1806.03568/) (2018)
- [Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation](https://mlsanity.com/paper/1805.03352/) (2018)
- [The FacT: Taming Latent Factor Models for Explainability with Factorization Trees](https://mlsanity.com/paper/1906.02037/) (2019)
- [A Capsule Network for Recommendation and Explaining What You Like and Dislike](https://mlsanity.com/paper/1907.00687/) (2019)
- [Persona-Aware Tips Generation](https://mlsanity.com/paper/1903.02156/) (2019)
- [Efficient Summarization with Read-Again and Copy Mechanism](https://mlsanity.com/paper/1611.03382/) (2016)

## Built on by (most cited first, 9 of 9)

- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [Comparative Explanations of Recommendations](https://mlsanity.com/paper/2111.00670/) (2021)
- [COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation](https://mlsanity.com/paper/2210.15500/) (2022)
- [SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction](https://mlsanity.com/paper/2510.00080/) (2025)
- [Graph-based Extractive Explainer for Recommendations](https://mlsanity.com/paper/2202.09730/) (2022)
- [Towards the design of user-centric strategy recommendation systems for collaborative Human-AI tasks](https://mlsanity.com/paper/2301.08144/) (2023)
- [Knowledge-grounded Natural Language Recommendation Explanation](https://mlsanity.com/paper/2308.15813/) (2023)
- [Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation](https://mlsanity.com/paper/2410.13248/) (2024)
- ["This Suits You the Best": Query Focused Comparative Explainable Summarization](https://mlsanity.com/paper/2507.04733/) (2025)

## Abstract (arXiv)

Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are often separately modeled as rating prediction and content generation tasks. In this work, we propose to strengthen their connection by enforcing the idea of sentiment alignment between a recommendation and its corresponding explanation. At training time, the two learning tasks are joined by a latent sentiment vector, which is encoded by the recommendation module and used to make word choices for explanation generation. At both training and inference time, the explanation module is required to generate explanation text that matches sentiment predicted by the recommendation module. Extensive experiments demonstrate our solution outperforms a rich set of baselines in both recommendation and explanation tasks, especially on the improved quality of its generated explanations. More importantly, our user studies confirm our generated explanations help users better recognize the differences between recommended items and understand why an item is recommended.