mlsanityData to 14 Oct 2026

COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation

arXiv 2210.15500 ↗First posted 14 Oct 2022cs.CL cs.CY cs.IRcited by 6

Not on the map. Why?

Abstract (arXiv)

As language models become increasingly integrated into our digital lives, Personalized Text Generation (PTG) has emerged as a pivotal component with a wide range of applications. However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different levels of linguistic quality with users' protected attributes. The model can inherit the bias and perpetuate inequality in generating text w.r.t. users' protected attributes, leading to unfair treatment when serving users. In this work, we investigate fairness of PTG in the context of personalized explanation generation for recommendations. We first discuss the biases in generated explanations and their fairness implications. To promote fairness, we introduce a general framework to achieve measure-specific counterfactual fairness in explanation generation. Extensive experiments and human evaluations demonstrate the effectiveness of our method.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 55 of its 83 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

55 of 83 references.

References · 55

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2018Hierarchical Neural Story Generationcited by 1,193
  6. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  7. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  8. 2017Counterfactual Fairnesscited by 804
  9. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  10. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  11. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  12. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
38 more
  1. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  2. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  3. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  4. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  5. 2017Toward Controlled Generation of Textcited by 272
  6. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  7. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  8. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  9. 2021Societal Biases in Language Generation: Progress and Challengescited by 202
  10. 2018Fairness of Exposure in Rankingscited by 190
  11. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  12. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  13. 2019On the Fairness of Disentangled Representationscited by 144
  14. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  15. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  16. 2019Learning Disentangled Representations for Recommendationcited by 110
  17. 2020Robust Optimization for Fairness with Noisy Protected Groupscited by 78
  18. 2019PC-Fairness: A Unified Framework for Measuring Causality-based Fairnesscited by 67
  19. 2019Counterfactual Risk Assessments, Evaluation, and Fairnesscited by 59
  20. 2021Personalized Transformer for Explainable Recommendationcited by 59
  21. 2020Survey on Causal-based Machine Learning Fairness Notionscited by 54
  22. 2020Investigating African-American Vernacular English in Transformer-Based Text Generationcited by 53
  23. 2017Neural Rating Regression with Abstractive Tips Generation for Recommendationcited by 50
  24. 2016Personalized Machine Translation: Preserving Original Author Traitscited by 47
  25. 2018Explainable Recommendation via Multi-Task Learning in Opinionated Text Datacited by 40
  26. 2019Fair Classification and Social Welfarecited by 40
  27. 2021Personalized Counterfactual Fairness in Recommendationcited by 38
  28. 2020GRUEN for Evaluating Linguistic Quality of Generated Textcited by 37
  29. 2019Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causalitycited by 33
  30. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  31. 2019Towards Controllable and Personalized Review Generationcited by 24
  32. 2020User Fairness, Item Fairness, and Diversity for Rankings in Two-Sided Marketscited by 23
  33. 2021Generate Natural Language Explanations for Recommendationcited by 23
  34. 2017Neural Personalized Response Generation as Domain Adaptationcited by 19
  35. 2021PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Modelscited by 17
  36. 2018Controlling Personality-Based Stylistic Variation with Neural Natural Language Generatorscited by 14
  37. 2015Fairness Constraints: Mechanisms for Fair Classificationcited by 10
  38. 2020Non-Clicks Mean Irrelevant? Propensity Ratio Scoring As a Correctioncited by 10

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 73
  2. 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
  3. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
  4. 2023Counterfactually Fair Representationcited by 9
  5. 2025Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelinescited by 2
  6. 2024Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insightscited by 0