mlsanityData to 14 Oct 2026

Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback

arXiv 2605.29141 ↗First posted 27 May 2026cs.IR cs.AIcited by 1

On the map: LLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG

Abstract (arXiv)

Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, like comments and reviews. This explicit context feedback captures the nuanced reasons behind user decisions regarding their preferences. In addition, it offers critical heterogeneous information for user preference alignment and more explainable recommendations. Overlooking such signals can lead to misaligned user preferences and further reinforce filter bubbles, as algorithms fail to understand the "semantic context" behind user choices. Recent advances in Large Language Models (LLMs) present new opportunities to harness user-generated content for more accurate and diverse recommendations, yet current LLM-based recommendations still focus on using item meta-data and underutilize this resource. In this paper, we advocate for prioritizing explicit context feedback in the next generation of LLM-based RecSys. We review the evolution of recommendation paradigms, highlight the value of context-rich feedback, call for new benchmarks and metrics, and introduce frameworks for integrating explicit user signals into scalable LLM-driven RecSys. Centering on user-preference modeling, we aim to foster more personalized, transparent, and explainable RecSys online platforms.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 50 of its 82 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

50 of 82 references.

References · 50

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2018Self-Attentive Sequential Recommendationcited by 1,184
  4. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  5. 2017Neural Collaborative Filteringcited by 1,111
  6. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  7. 2016Wide & Deep Learning for Recommender Systemscited by 747
  8. 2015Image-based Recommendations on Styles and Substitutescited by 706
  9. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  10. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  11. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  12. 2017Deep & Cross Network for Ad Click Predictionscited by 393
38 more
  1. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
  2. 2020Self-supervised Graph Learning for Recommendationcited by 305
  3. 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 240
  4. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  5. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  6. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  7. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
  8. 2023Text Is All You Need: Learning Language Representations for Sequential Recommendationcited by 149
  9. 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
  10. 2021UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendationcited by 87
  11. 2017Joint Deep Modeling of Users and Items Using Reviews for Recommendationcited by 84
  12. 2021Contrastive Learning for Cold-Start Recommendationcited by 79
  13. 2023A Survey on Popularity Bias in Recommender Systemscited by 43
  14. 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequencecited by 33
  15. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  16. 2020ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendationcited by 22
  17. 2023Knowledge Graph Self-Supervised Rationalization for Recommendationcited by 22
  18. 2024RDRec: Rationale Distillation for LLM-based Recommendationcited by 22
  19. 2025Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmapcited by 20
  20. 2022A Review-aware Graph Contrastive Learning Framework for Recommendationcited by 18
  21. 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
  22. 2025LLM-based User Profile Management for Recommender Systemcited by 10
  23. 2024Review-based Recommender Systems: A Survey of Approaches, Challenges and Future Perspectivescited by 8
  24. 2023Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenderscited by 7
  25. 2025LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendationcited by 7
  26. 2020Learning Hierarchical Review Graph Representations for Recommendationcited by 6
  27. 2025User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systemscited by 6
  28. 2023Graph Neural Ordinary Differential Equations-based method for Collaborative Filteringcited by 5
  29. 2024Mixed Supervised Graph Contrastive Learning for Recommendationcited by 3
  30. 2024Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendationcited by 3
  31. 2025Beyond Explicit and Implicit: How Users Provide Feedback to Shape Personalized Recommendation Contentcited by 3
  32. 2022Disentangled Graph Contrastive Learning for Review-based Recommendationcited by 2
  33. 2023Graph-based Village Level Poverty Identificationcited by 2
  34. 2025Graph Neural Controlled Differential Equations For Collaborative Filteringcited by 2
  35. 2021Rating and aspect-based opinion graph embeddings for explainable recommendationscited by 1
  36. 2024Item Cluster-aware Prompt Learning for Session-based Recommendationcited by 1
  37. 2025A Contrastive Framework with User, Item and Review Alignment for Recommendationcited by 1
  38. 2025SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026BehaviorBench: Modeling Real-World User Decisions from Behavioral Tracescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
  2. 2025Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
  3. 2025Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs
  4. 2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
  5. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
  6. 2025Effectiveness of LLMs in Temporal User Profiling for Recommendation
  7. 2026CoNRec: Context-Discerning Negative Recommendation with LLMs
  8. 2024Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems