mlsanityData to 7 Oct 2026

CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs

arXiv 2602.00742 ↗First posted 31 Jan 2026cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder and a discrete prototype codebook to extract multi-dimensional user traits. This design enables plug-and-play personalization with a small number of trainable parameters (about 20M parameters, about 0.2% of the total model size). Through extensive experiments on variant generation tasks, we show that CURP achieves superior performance and generalization compared to strong baselines, while offering better interpretability and scalability. The code are available at https://github.com/RaidonWong/CURPcode

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

33 of 58 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  9. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  10. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  11. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 167
  12. 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningcited by 147
21 more
  1. 2024Personalized Language Modeling from Personalized Human Feedbackcited by 124
  2. 2024LongLaMP: A Benchmark for Personalized Long-form Text Generationcited by 91
  3. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
  4. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  5. 2024Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Effortscited by 71
  6. 2023Generative Recommendation: Towards Next-generation Recommender Paradigmcited by 69
  7. 2025Personalized Generation In Large Model Era: A Surveycited by 45
  8. 2024Personalized Large Language Modelscited by 44
  9. 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 34
  10. 2024Personalized LLM Response Generation with Parameterized Memory Injectioncited by 33
  11. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  12. 2024User Modeling and User Profiling: A Comprehensive Surveycited by 29
  13. 2024User Embedding Model for Personalized Language Promptingcited by 28
  14. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 28
  15. 2023A Survey on User Behavior Modeling in Recommender Systemscited by 26
  16. 2025PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptationcited by 22
  17. 2024Guided Profile Generation Improves Personalization with LLMscited by 19
  18. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  19. 2024PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Promptingcited by 13
  20. 2024PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulationcited by 8
  21. 2024MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Spacecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalizationcited by 3
  2. 2026Large Behavior Model: A Promptable Digital Twin of the Retail Customercited by 1
  3. 2026Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalizationcited by 0