mlsanityData to 14 Oct 2026

Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation

arXiv 2510.05125 ↗First posted 30 Sep 2025cs.CL cs.LGcited by 1

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

While collaborative filtering delivers predictive accuracy and efficiency, and Large Language Models (LLMs) enable expressive and generalizable reasoning, modern recommendation systems must bring these strengths together. Growing user expectations, such as natural-language queries and transparent explanations, further highlight the need for a unified approach. However, doing so is nontrivial. Collaborative signals are often token-efficient but semantically opaque, while LLMs are semantically rich but struggle to model implicit user preferences when trained only on textual inputs. This paper introduces Item-ID + Oral-language Mixture-of-Experts Language Model (IDIOMoE), which treats item interaction histories as a native dialect within the language space, enabling collaborative signals to be understood in the same way as natural language. By splitting the Feed Forward Network of each block of a pretrained LLM into a separate text expert and an item expert with token-type gating, our method avoids destructive interference between text and catalog modalities. IDIOMoE demonstrates strong recommendation performance across both public and proprietary datasets, while preserving the text understanding of the pretrained model.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 81 of its 115 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

81 of 115 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models9 Jul

Other references · 80

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2016Pointer Sentinel Mixture Modelscited by 3,096
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  8. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  9. 2018Self-Attentive Sequential Recommendationcited by 1,184
  10. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  11. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  12. 2015Image-based Recommendations on Styles and Substitutescited by 706
38 more
  1. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  2. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 532
  3. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 425
  4. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  5. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  6. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  7. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
  8. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 300
  9. 2023Recommender Systems with Generative Retrievalcited by 198
  10. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
  11. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  12. 2018Towards Deep Conversational Recommendationscited by 176
  13. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
  14. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  15. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 161
  16. 2022M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systemscited by 152
  17. 2015VBPR: Visual Bayesian Personalized Ranking from Implicit Feedbackcited by 151
  18. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 142
  19. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 134
  20. 2023Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisitedcited by 124
  21. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 121
  22. 2018A Simple Convolutional Generative Network for Next Item Recommendationcited by 120
  23. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  24. 2022Learning Vector-Quantized Item Representation for Transferable Sequential Recommenderscited by 112
  25. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 108
  26. 2023GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretationcited by 103
  27. 2023How to Index Item IDs for Recommendation Foundation Modelscited by 102
  28. 2023Scaling Vision-Language Models with Sparse Mixture of Expertscited by 88
  29. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 82
  30. 2023A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systemscited by 73
  31. 2023Generative Recommendation: Towards Next-generation Recommender Paradigmcited by 70
  32. 2023Collaborative Large Language Model for Recommender Systemscited by 64
  33. 2024IDGenRec: LLM-RecSys Alignment with Textual ID Learningcited by 53
  34. 2025MTGR: Industrial-Scale Generative Recommendation Framework in Meituancited by 49
  35. 2023VIP5: Towards Multimodal Foundation Models for Recommendationcited by 46
  36. 2025EVEv2: Improved Baselines for Encoder-Free Vision-Language Modelscited by 41
  37. 2024Large Language Models for Next Point-of-Interest Recommendationcited by 40
  38. 2023E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendationcited by 39

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Model Driven Recommendation
  2. 2026A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
  3. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences
  4. 2025LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
  5. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond
  6. 2025EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
  7. 2025Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
  8. 2024Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization