mlsanityData to 7 Oct 2026

Degenerate Feedback Loops in Recommender Systems

arXiv 1902.10730 ↗First posted 27 Feb 2019stat.ML cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

Machine learning is used extensively in recommender systems deployed in products. The decisions made by these systems can influence user beliefs and preferences which in turn affect the feedback the learning system receives - thus creating a feedback loop. This phenomenon can give rise to the so-called "echo chambers" or "filter bubbles" that have user and societal implications. In this paper, we provide a novel theoretical analysis that examines both the role of user dynamics and the behavior of recommender systems, disentangling the echo chamber from the filter bubble effect. In addition, we offer practical solutions to slow down system degeneracy. Our study contributes toward understanding and developing solutions to commonly cited issues in the complex temporal scenario, an area that is still largely unexplored.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 17; 2023: 11; 2024: 16; 2025: 3; 2026: 11.

67 papers.

Sort:

By area:

  1. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  2. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  3. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  4. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 59
  5. 2023Towards Understanding the Interplay of Generative Artificial Intelligence and the Internetcited by 54
  6. 2023Performative Prediction: Past and Futurecited by 52
  7. 2024Y Social: an LLM-powered Social Media Digital Twincited by 43
  8. 2024AI and the Problem of Knowledge Collapsecited by 34
  9. 2022Estimating and Penalizing Induced Preference Shifts in Recommender Systemscited by 29
  10. 2023Human-AI Coevolutioncited by 27
  11. 2022Preference Dynamics Under Personalized Recommendationscited by 25
  12. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparitiescited by 25
38 more
  1. 2021User Tampering in Reinforcement Learning Recommender Systemscited by 23
  2. 2025iAgent: LLM Agent as a Shield between User and Recommender Systemscited by 23
  3. 2021Measuring Recommender System Effects with Simulated Userscited by 20
  4. 2021Correcting Exposure Bias for Link Recommendationcited by 17
  5. 2022Breaking Feedback Loops in Recommender Systems with Causal Inferencecited by 14
  6. 2022DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systemscited by 14
  7. 2021T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systemscited by 12
  8. 2023Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendationscited by 12
  9. 2023Scalable Neural Contextual Bandit for Recommender Systemscited by 12
  10. 2021A Survey on Echo Chambers on Social Media: Description, Detection and Mitigationcited by 11
  11. 2024Accounting for AI and Users Shaping One Another: The Role of Mathematical Modelscited by 11
  12. 2021The Stereotyping Problem in Collaboratively Filtered Recommender Systemscited by 10
  13. 2024Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutionscited by 9
  14. 2022Towards Psychologically-Grounded Dynamic Preference Modelscited by 8
  15. 2022Auditing YouTube's Recommendation Algorithm for Misinformation Filter Bubblescited by 7
  16. 2024Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairnesscited by 6
  17. 2021Addressing the Long-term Impact of ML Decisions via Policy Regretcited by 5
  18. 2024Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answeringcited by 5
  19. 2024Harm Mitigation in Recommender Systems under User Preference Dynamicscited by 5
  20. 2024From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learningcited by 5
  21. 2022Manifestations of Xenophobia in AI Systemscited by 4
  22. 2022On the Generalizability and Predictability of Recommender Systemscited by 3
  23. 2024Performative Debias with Fair-exposure Optimization Driven by Strategic Agents in Recommender Systemscited by 3
  24. 2021Recommendation System Simulations: A Discussion of Two Key Challengescited by 2
  25. 2022Two-Stage Neural Contextual Bandits for Personalised News Recommendationcited by 2
  26. 2022Dynamic Causal Collaborative Filteringcited by 2
  27. 2022Contextual bandits with concave rewards, and an application to fair rankingcited by 2
  28. 2023Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigationcited by 2
  29. 2024Algorithmic Fairness: A Tolerance Perspectivecited by 2
  30. 2024System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processescited by 2
  31. 2024Flexible Generation of Preference Data for Recommendation Analysiscited by 2
  32. 2021Existence conditions for hidden feedback loops in online recommender systemscited by 1
  33. 2022Solutions to preference manipulation in recommender systems require knowledge of meta-preferencescited by 1
  34. 2023Simulating News Recommendation Ecosystem for Fun and Profitcited by 1
  35. 2024A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systemscited by 1
  36. 2024Content-Agnostic Moderation for Stance-Neutral Recommendationcited by 1
  37. 2024User-Creator Feature Polarization in Recommender Systems with Dual Influencecited by 1
  38. 2024Reducing Popularity Influence by Addressing Position Biascited by 1

50 most cited of 67 All 67 (JSON)