mlsanityData to 14 Oct 2026

PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation

arXiv 2601.16556 ↗First posted 23 Jan 2026cs.IR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-based quantization. Despite its great potential in unifying retrieval and ranking, existing GSR frameworks still face two critical limitations: (1) impure and unstable semantic tokenization, where quantization methods struggle with interaction noise and codebook collapse, resulting in SIDs with ambiguous discrimination; and (2) lossy and weakly structured generation, where reliance solely on coarse-grained discrete tokens inevitably introduces information loss and neglects items' hierarchical logic. To address these issues, we propose a novel generative recommendation framework, PRISM, with Purified Representation and Integrated Semantic Modeling. Specifically, to ensure high-quality tokenization, we design a Purified Semantic Quantizer that constructs a robust codebook via adaptive collaborative denoising and hierarchical semantic anchoring mechanisms. To compensate for information loss during quantization, we further propose an Integrated Semantic Recommender, which incorporates a dynamic semantic integration mechanism to integrate fine-grained semantics and enforces logical validity through a semantic structure alignment objective. PRISM consistently outperforms state-of-the-art baselines across four real-world datasets, demonstrating substantial performance gains, particularly in high-sparsity scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 78 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

49 of 78 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Layer Normalizationcited by 5,669
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2018Self-Attentive Sequential Recommendationcited by 1,184
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  9. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  10. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  11. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  12. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
37 more
  1. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  2. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  3. 2023A Survey on Large Language Models for Recommendationcited by 379
  4. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  5. 2018Variational Autoencoders for Collaborative Filteringcited by 310
  6. 2020Self-supervised Graph Learning for Recommendationcited by 305
  7. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
  8. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  9. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
  10. 2018A Simple Convolutional Generative Network for Next Item Recommendationcited by 120
  11. 2022Learning Vector-Quantized Item Representation for Transferable Sequential Recommenderscited by 112
  12. 2019Hierarchical Gating Networks for Sequential Recommendationcited by 101
  13. 2023Generative Recommendation: Towards Next-generation Recommender Paradigmcited by 70
  14. 2023GenRec: Large Language Model for Generative Recommendationcited by 63
  15. 2024HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modelingcited by 63
  16. 2024EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaborationcited by 58
  17. 2024TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendationcited by 35
  18. 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representationscited by 35
  19. 2024Generative Recommender with End-to-End Learnable Item Tokenizationcited by 34
  20. 2024LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systemscited by 21
  21. 2025Order-agnostic Identifier for Large Language Model-based Generative Recommendationcited by 21
  22. 2025Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendationcited by 15
  23. 2025Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrievalcited by 13
  24. 2025Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Modelcited by 13
  25. 2025HiD-VAE: Interpretable Generative Recommendation via Hierarchical and Disentangled Semantic IDscited by 12
  26. 2024Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decodingcited by 10
  27. 2025The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exitcited by 10
  28. 2025Efficient Beam Search for Large Language Models Using Trie-Based Decodingcited by 10
  29. 2024Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenizationcited by 9
  30. 2025DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendationcited by 8
  31. 2025A Survey on Large Language Models in Multimodal Recommender Systemscited by 7
  32. 2025Understanding Generative Recommendation with Semantic IDs from a Model-scaling Viewcited by 6
  33. 2024Improving LLMs for Recommendation with Out-Of-Vocabulary Tokenscited by 5
  34. 2025BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendationcited by 5
  35. 2025CAT-ID2: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commercecited by 5
  36. 2025Align3GR: Unified Multi-Level Alignment for LLM-based Generative Recommendationcited by 5
  37. 2022Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization
  2. 2025CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
  3. 2025Semantics Meet Signals: Dual Codebook Representationl Learning for Generative Recommendation
  4. 2026Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding
  5. 2025LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation
  6. 2026Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
  7. 2025REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems
  8. 2026Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation