mlsanityData to 14 Oct 2026

GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion

arXiv 2506.01673 ↗First posted 2 Jun 2025cs.IR cs.AI cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Generative recommendation is an emerging paradigm that leverages the extensive knowledge of large language models by formulating recommendations into a text-to-text generation task. However, existing studies face two key limitations in (i) incorporating implicit item relationships and (ii) utilizing rich yet lengthy item information. To address these challenges, we propose a Generative Recommender via semantic-Aware Multi-granular late fusion (GRAM), introducing two synergistic innovations. First, we design semantic-to-lexical translation to encode implicit hierarchical and collaborative item relationships into the vocabulary space of LLMs. Second, we present multi-granular late fusion to integrate rich semantics efficiently with minimal information loss. It employs separate encoders for multi-granular prompts, delaying the fusion until the decoding stage. Experiments on four benchmark datasets show that GRAM outperforms eight state-of-the-art generative recommendation models, achieving significant improvements of 11.5-16.0% in Recall@5 and 5.3-13.6% in NDCG@5. The source code is available at https://github.com/skleee/GRAM.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

42 of 58 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2018Self-Attentive Sequential Recommendationcited by 1,184
  8. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  9. 2015Image-based Recommendations on Styles and Substitutescited by 706
  10. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  11. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  12. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
30 more
  1. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  2. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  3. 2023A Survey on Large Language Models for Recommendationcited by 379
  4. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  5. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  6. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  7. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
  8. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  9. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
  10. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
  11. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 161
  12. 2023Text Is All You Need: Learning Language Representations for Sequential Recommendationcited by 149
  13. 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
  14. 2024Learnable Item Tokenization for Generative Recommendationcited by 110
  15. 2023How to Index Item IDs for Recommendation Foundation Modelscited by 102
  16. 2019Hierarchical Gating Networks for Sequential Recommendationcited by 101
  17. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 100
  18. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  19. 2022Intent Contrastive Learning for Sequential Recommendationcited by 91
  20. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 73
  21. 2024IDGenRec: LLM-RecSys Alignment with Textual ID Learningcited by 53
  22. 2022FiDO: Fusion-in-Decoder optimized for stronger performance and faster inferencecited by 31
  23. 2023Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendationcited by 29
  24. 2024Text-like Encoding of Collaborative Information in Large Language Models for Recommendationcited by 25
  25. 2024CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendationcited by 24
  26. 2023GLEN: Generative Retrieval via Lexical Index Learningcited by 17
  27. 2023Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendationscited by 16
  28. 2023Text Matching Improves Sequential Recommendation by Reducing Popularity Biasescited by 10
  29. 2024Enhancing High-order Interaction Awareness in LLM-based Recommender Modelcited by 8
  30. 2022SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrievalcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Sequential Data Augmentation for Generative Recommendationcited by 2
  2. 2025Enhancing Time Awareness in Generative Recommendationcited by 2
  3. 2026From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Enginescited by 1
  4. 2026Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillationcited by 0
  5. 2026On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategiescited by 0
  6. 2026Auditing Semantic Gains in Sequential Recommendation: A Lightweight Recovery Testcited by 0
  7. 2026P3Rec: Distilling Prior--Posterior Preference Reasoning for LLM-based Recommendationcited by 0