mlsanityData to 7 Oct 2026

Factual and Informative Review Generation for Explainable Recommendation

arXiv 2209.12613 ↗First posted 12 Sep 2022cs.CL cs.AI cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Recent models can generate fluent and grammatical synthetic reviews while accurately predicting user ratings. The generated reviews, expressing users' estimated opinions towards related products, are often viewed as natural language 'rationales' for the jointly predicted rating. However, previous studies found that existing models often generate repetitive, universally applicable, and generic explanations, resulting in uninformative rationales. Further, our analysis shows that previous models' generated content often contain factual hallucinations. These issues call for novel solutions that could generate both informative and factually grounded explanations. Inspired by recent success in using retrieved content in addition to parametric knowledge for generation, we propose to augment the generator with a personalized retriever, where the retriever's output serves as external knowledge for enhancing the generator. Experiments on Yelp, TripAdvisor, and Amazon Movie Reviews dataset show our model could generate explanations that more reliably entail existing reviews, are more diverse, and are rated more informative by human evaluators.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

33 of 46 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  7. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  9. 2016Wide & Deep Learning for Recommender Systemscited by 745
  10. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  11. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  12. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
21 more
  1. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  2. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
  3. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  4. 2020Measuring Association Between Labels and Free-Text Rationalescited by 159
  5. 2021Explaining Answers with Entailment Treescited by 148
  6. 2020Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Spacecited by 114
  7. 2022Personalized Prompt Learning for Explainable Recommendationcited by 79
  8. 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
  9. 2021Few-Shot Question Answering by Pretraining Span Selectioncited by 62
  10. 2018Training Classifiers with Natural Language Explanationscited by 58
  11. 2021Personalized Transformer for Explainable Recommendationcited by 58
  12. 2017Neural Rating Regression with Abstractive Tips Generation for Recommendationcited by 50
  13. 2020Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphscited by 46
  14. 2021General-Purpose Question-Answering with Macawcited by 40
  15. 2020Unsupervised Opinion Summarization with Noising and Denoisingcited by 37
  16. 2020Towards Interpretable Natural Language Understanding with Explanations as Latent Variablescited by 30
  17. 2022Rethinking and Refining the Distinct Metriccited by 27
  18. 2021Learning Opinion Summarizers by Selecting Informative Reviewscited by 25
  19. 2021Convex Aggregation for Opinion Summarizationcited by 21
  20. 2021Unsupervised Enrichment of Persona-grounded Dialog with Background Storiescited by 14
  21. 2021Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Trainingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 2; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  2. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  3. 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language Modelscited by 25
  4. 2024Are Large Language Models Good at Utility Judgments?cited by 22
  5. 2023NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegiancited by 9
  6. 2023RRAML: Reinforced Retrieval Augmented Machine Learningcited by 6
  7. 2024Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Modelscited by 6
  8. 2024MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendationcited by 3
  9. 2024Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendationcited by 3
  10. 2024GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendationcited by 2
  11. 2025Explainable Recommendation with Simulated Human Feedbackcited by 1
  12. 2024Large Language Model Driven Recommendationcited by 0
2 more
  1. 2026CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networkscited by 0
  2. 2026LLMs Should Incorporate Explicit Mechanisms for Human Empathycited by 0