# Automatic Generation of Natural Language Explanations

arXiv: https://arxiv.org/abs/1707.01561 · HTML: https://mlsanity.com/paper/1707.01561/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2017.

## Built on by (most cited first, 22 of 22)

- [SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales](https://mlsanity.com/paper/2405.20974/) (2024)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Generate Natural Language Explanations for Recommendation](https://mlsanity.com/paper/2101.03392/) (2021)
- [Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges](https://mlsanity.com/paper/2405.15604/) (2024)
- [Explainability in Music Recommender Systems](https://mlsanity.com/paper/2201.10528/) (2022)
- [SQLucid: Grounding Natural Language Database Queries with Interactive Explanations](https://mlsanity.com/paper/2409.06178/) (2024)
- [IRIS: Interpretable Rubric-Informed Segmentation for Action Quality Assessment](https://mlsanity.com/paper/2303.09097/) (2023)
- [Categorical Foundations of Explainable AI: A Unifying Theory](https://mlsanity.com/paper/2304.14094/) (2023)
- [Explanatory Summarization with Discourse-Driven Planning](https://mlsanity.com/paper/2504.19339/) (2025)
- [Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models](https://mlsanity.com/paper/2309.10444/) (2023)
- [Counterfactually Evaluating Explanations in Recommender Systems](https://mlsanity.com/paper/2203.01310/) (2022)
- [Towards Human-Centred Explainability Benchmarks For Text Classification](https://mlsanity.com/paper/2211.05452/) (2022)
- [GPT as a Baseline for Recommendation Explanation Texts](https://mlsanity.com/paper/2309.08817/) (2023)
- [CrystalCandle: A User-Facing Model Explainer for Narrative Explanations](https://mlsanity.com/paper/2105.12941/) (2021)
- [Learning to Counterfactually Explain Recommendations](https://mlsanity.com/paper/2211.09752/) (2022)
- [A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations](https://mlsanity.com/paper/2507.10585/) (2025)
- [A big data approach towards sarcasm detection in Russian](https://mlsanity.com/paper/2306.00445/) (2023)
- [Robust Explainable Recommendation](https://mlsanity.com/paper/2405.01855/) (2024)
- [CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews](https://mlsanity.com/paper/2504.13993/) (2025)
- [ELIXIR: Efficient and LIghtweight model for eXplaIning Recommendations](https://mlsanity.com/paper/2508.20312/) (2025)
- [Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation](https://mlsanity.com/paper/2601.03608/) (2025)
- [Visual or Textual: Effects of Explanation Format and Personal Characteristics on the Perception of Explanations in an Educational Recommender System](https://mlsanity.com/paper/2603.25624/) (2026)

## Abstract (arXiv)

An important task for recommender system is to generate explanations according to a user's preferences. Most of the current methods for explainable recommendations use structured sentences to provide descriptions along with the recommendations they produce. However, those methods have neglected the review-oriented way of writing a text, even though it is known that these reviews have a strong influence over user's decision. In this paper, we propose a method for the automatic generation of natural language explanations, for predicting how a user would write about an item, based on user ratings from different items' features. We design a character-level recurrent neural network (RNN) model, which generates an item's review explanations using long-short term memories (LSTM). The model generates text reviews given a combination of the review and ratings score that express opinions about different factors or aspects of an item. Our network is trained on a sub-sample from the large real-world dataset BeerAdvocate. Our empirical evaluation using natural language processing metrics shows the generated text's quality is close to a real user written review, identifying negation, misspellings, and domain specific vocabulary.