mlsanityData to 14 Oct 2026

Aligning Recommendations with User Popularity Preferences

arXiv 2604.01036 ↗First posted 1 Apr 2026cs.IR cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Popularity bias is a pervasive problem in recommender systems, where recommendations disproportionately favor popular items. This not only results in "rich-get-richer" dynamics and a homogenization of visible content, but can also lead to misalignment of recommendations with individual users' preferences for popular or niche content. This work studies popularity bias through the lens of user-recommender alignment. To this end, we introduce Popularity Quantile Calibration, a measurement framework that quantifies misalignment between a user's historical popularity preference and the popularity of their recommendations. Building on this notion of popularity alignment, we propose SPREE, an inference-time mitigation method for sequential recommenders based on activation steering. SPREE identifies a popularity direction in representation space and adaptively steers model activations based on an estimate of each user's personal popularity bias, allowing both the direction and magnitude of steering to vary across users. Unlike global debiasing approaches, SPREE explicitly targets alignment rather than uniformly reducing popularity. Experiments across multiple datasets show that SPREE consistently improves user-level popularity alignment while preserving recommendation quality.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 51 of its 85 references that are in the map. First posted on arXiv 1 Apr 2026.

Builds on

51 of 85 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  4. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  5. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  6. 2018Self-Attentive Sequential Recommendationcited by 1,184
  7. 2017Neural Collaborative Filteringcited by 1,111
  8. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 1,032
  9. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  10. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  11. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  12. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
38 more
  1. 2019Measurement and Fairnesscited by 308
  2. 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 245
  3. 2023Recommender Systems with Generative Retrievalcited by 198
  4. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  5. 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 160
  6. 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimizationcited by 118
  7. 2019Distribution Calibration for Regressioncited by 89
  8. 2019Evaluating and Calibrating Uncertainty Prediction in Regression Taskscited by 87
  9. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 82
  10. 2017Translation-based Recommendationcited by 71
  11. 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steeringcited by 66
  12. 2025Position: Evaluating Generative AI Systems Is a Social Science Measurement Challengecited by 63
  13. 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
  14. 2024Spectral Editing of Activations for Large Language Model Alignmentcited by 56
  15. 2023A Survey on Popularity Bias in Recommender Systemscited by 43
  16. 2021User-centered Evaluation of Popularity Bias in Recommender Systemscited by 38
  17. 2020The Connection Between Popularity Bias, Calibration, and Fairness in Recommendationcited by 35
  18. 2022Fairness in Recommender Systems: Research Landscape and Future Directionscited by 30
  19. 2023gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Samplingcited by 29
  20. 2025To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Modelscited by 29
  21. 2024Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recencycited by 28
  22. 2024Large Language Models as Recommender Systems: A Study of Popularity Biascited by 26
  23. 2024Evaluating Generative AI Systems is a Social Science Measurement Challengecited by 23
  24. 2023Fairness and Diversity in Recommender Systems: A Surveycited by 22
  25. 2017How algorithmic popularity bias hinders or promotes qualitycited by 20
  26. 2019Multi-stakeholder Recommendation and its Connection to Multi-sided Fairnesscited by 19
  27. 2024Discovering Bias in Latent Space: An Unsupervised Debiasing Approachcited by 15
  28. 2025Semantic IDs for Joint Generative Search and Recommendationcited by 14
  29. 2024A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impactscited by 13
  30. 2022Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspectivecited by 11
  31. 2021Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?cited by 9
  32. 2024Debiasing Recommendation with Personal Popularitycited by 7
  33. 2024Enhancing Sequential Music Recommendation with Personalized Popularity Awarenesscited by 7
  34. 2024Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Modelscited by 4
  35. 2023Metrics for popularity bias in dynamic recommender systemscited by 3
  36. 2025Text2Tracks: Prompt-based Music Recommendation via Generative Retrievalcited by 3
  37. 2024Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendationscited by 2
  38. 2025On Optimal Steering to Achieve Exact Fairnesscited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback
  2. 2025Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
  3. 2022Causal Intervention for Fairness in Multi-behavior Recommendation
  4. 2025Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines
  5. 2024Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
  6. 2025CM3: Calibrating Multimodal Recommendation
  7. 2025What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
  8. 2025Tree of Preferences for Diversified Recommendation