# On Faithfulness and Coherence of Language Explanations for Recommendation Systems

arXiv: https://arxiv.org/abs/2209.05409 · HTML: https://mlsanity.com/paper/2209.05409/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [Personalized Transformer for Explainable Recommendation](https://mlsanity.com/paper/2105.11601/) (2021)
- [Rethinking Explainability as a Dialogue: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01875/) (2022)
- [Neural Rating Regression with Abstractive Tips Generation for Recommendation](https://mlsanity.com/paper/1708.00154/) (2017)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [Multi-Pointer Co-Attention Networks for Recommendation](https://mlsanity.com/paper/1801.09251/) (2018)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [Towards Controllable and Personalized Review Generation](https://mlsanity.com/paper/1910.03506/) (2019)
- [How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements](https://mlsanity.com/paper/2005.12210/) (2020)
- [Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?](https://mlsanity.com/paper/2203.06487/) (2022)
- [Knowledge-based Review Generation by Coherence Enhanced Text Planning](https://mlsanity.com/paper/2105.03815/) (2021)

## Built on by (most cited first, 1 of 1)

- [The Problem of Coherence in Natural Language Explanations of Recommendations](https://mlsanity.com/paper/2312.11356/) (2023)

## Abstract (arXiv)

Reviews contain rich information about product characteristics and user interests and thus are commonly used to boost recommender system performance. Specifically, previous work show that jointly learning to perform review generation improves rating prediction performance. Meanwhile, these model-produced reviews serve as recommendation explanations, providing the user with insights on predicted ratings. However, while existing models could generate fluent, human-like reviews, it is unclear to what degree the reviews fully uncover the rationale behind the jointly predicted rating. In this work, we perform a series of evaluations that probes state-of-the-art models and their review generation component. We show that the generated explanations are brittle and need further evaluation before being taken as literal rationales for the estimated ratings.