mlsanityData to 14 Oct 2026

Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited

arXiv 2303.13835 ↗First posted 24 Mar 2023cs.IRcited by 124

Not on the map. Why?

Abstract (arXiv)

Recommendation models that utilize unique identities (IDs) to represent distinct users and items have been state-of-the-art (SOTA) and dominated the recommender systems (RS) literature for over a decade. Meanwhile, the pre-trained modality encoders, such as BERT and ViT, have become increasingly powerful in modeling the raw modality features of an item, such as text and images. Given this, a natural question arises: can a purely modality-based recommendation model (MoRec) outperforms or matches a pure ID-based model (IDRec) by replacing the itemID embedding with a SOTA modality encoder? In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency. We aim to revisit this `old' question and systematically study MoRec from several aspects. Specifically, we study several sub-questions: (i) which recommendation paradigm, MoRec or IDRec, performs better in practical scenarios, especially in the general setting and warm item scenarios where IDRec has a strong advantage? does this hold for items with different modality features? (ii) can the latest technical advances from other communities (i.e., natural language processing and computer vision) translate into accuracy improvement for MoRec? (iii) how to effectively utilize item modality representation, can we use it directly or do we have to adjust it with new data? (iv) are there some key challenges for MoRec to be solved in practical applications? To answer them, we conduct rigorous experiments for item recommendations with two popular modalities, i.e., text and vision. We provide the first empirical evidence that MoRec is already comparable to its IDRec counterpart with an expensive end-to-end training method, even for warm item recommendation. Our results potentially imply that the dominance of IDRec in the RS field may be greatly challenged in the future.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Mar 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 20; 2024: 40; 2025: 43; 2026: 21.

124 papers.

Sort:

By area:

  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  2. 2023A Survey on Large Language Models for Recommendationcited by 379
  3. 2023Recommender Systems with Generative Retrievalcited by 198
  4. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  5. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  6. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  7. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 142
  8. 2023Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendationcited by 114
  9. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  10. 2023ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 77
  11. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  12. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
38 more
  1. 2024IDGenRec: LLM-RecSys Alignment with Textual ID Learningcited by 53
  2. 2023Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendationscited by 52
  3. 2025Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendationcited by 51
  4. 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
  5. 2024Customizing Language Models with Instance-wise LoRA for Sequential Recommendationcited by 32
  6. 2023MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendationcited by 31
  7. 2024Rethinking Large Language Model Architectures for Sequential Recommendationscited by 27
  8. 2024IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFTcited by 26
  9. 2024Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviorscited by 23
  10. 2024Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insightscited by 23
  11. 2024LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Applicationcited by 21
  12. 2024Stealthy Attack on Large Language Model based Recommendationcited by 19
  13. 2025LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendationcited by 19
  14. 2024Language Representations Can be What Recommenders Need: Findings and Potentialscited by 18
  15. 2025ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendationcited by 18
  16. 2024Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendationcited by 17
  17. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigmscited by 17
  18. 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulationcited by 16
  19. 2024Taxonomy-Guided Zero-Shot Recommendations with LLMscited by 15
  20. 2025Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendationcited by 15
  21. 2023Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendationcited by 13
  22. 2024Ads Recommendation in a Collapsed and Entangled Worldcited by 13
  23. 2023FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Predictioncited by 11
  24. 2023Text Matching Improves Sequential Recommendation by Reducing Popularity Biasescited by 10
  25. 2024EasyRec: Simple yet Effective Language Models for Recommendationcited by 10
  26. 2024ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systemscited by 10
  27. 2025MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptationcited by 10
  28. 2025Interactive Recommendation Agent with Active User Commandscited by 10
  29. 2026Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedbackcited by 10
  30. 2024Preference Diffusion for Recommendationcited by 9
  31. 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
  32. 2023LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendationcited by 8
  33. 2024Mitigating Propensity Bias of Large Language Models for Recommender Systemscited by 8
  34. 2024STAR: A Simple Training-free Approach for Recommendations using Large Language Modelscited by 8
  35. 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendationcited by 7
  36. 2024Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendationcited by 7
  37. 2024Scaling Sequential Recommendation Models with Transformerscited by 7
  38. 2025LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendationcited by 7

50 most cited of 124 All 124 (JSON)