mlsanityData to 7 Oct 2026

Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization

arXiv 2606.04547 ↗First posted 3 Jun 2026cs.IR cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Personalizing large language models requires adapting model behavior to individual users while preserving robustness and deployment-scale efficiency. Existing approaches typically personalize LLMs either at the input level, by retrieving user histories or constructing profile prompts, or at the parameter level, by maintaining user-specific parameter-efficient modules. The former makes personalization sensitive to retrieval quality and prompt design, whereas the latter incurs storage and maintenance costs that grow with the user population. To address these limitations, we propose TAP-PER (Temporal Attentive Prefix for PERsonalization), a prefix-based framework that encodes user preferences as learnable representations, avoiding the serialization of user histories into prompts and replacing heavy per-user adapters with lightweight user-state prefix embeddings. Inspired by personalized recommendation systems, TAP-PER decomposes user modeling into user-state and query-conditioned components, and incorporates temporal signals to capture the evolving nature of user interests. Experiments on six LaMP tasks show that TAP-PER consistently outperforms prompt-based and model-based baselines across classification, rating, and generation settings. Moreover, TAP-PER uses 130x fewer per-user parameters than OPPU and roughly half the total parameter footprint of PER-PCS at the 1,000-user scale, demonstrating scalable personalization without prompt-serialized histories or heavy per-user adapters.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

33 of 52 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2020Extracting Training Data from Large Language Modelscited by 2,144
  7. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  8. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  9. 2018Self-Attentive Sequential Recommendationcited by 1,169
  10. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  11. 2015Session-based Recommendations with Recurrent Neural Networkscited by 685
  12. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
21 more
  1. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 473
  2. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  3. 2023A Survey on Large Language Models for Recommendationcited by 378
  4. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 336
  5. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 271
  6. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 160
  7. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  8. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 98
  9. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  10. 2024Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Effortscited by 71
  11. 2022HyperPrompt: Prompt-based Task-Conditioning of Transformerscited by 67
  12. 2024Aligning LLMs with Individual Preferences via Interactioncited by 63
  13. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  14. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  15. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 47
  16. 2025PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptationcited by 22
  17. 2023Policy Space Diversity for Non-Transitive Gamescited by 15
  18. 2024Selective Prompting Tuning for Personalized Conversations with LLMscited by 15
  19. 2025Instant Personalized Large Language Model Adaptation via Hypernetworkcited by 15
  20. 2026CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMscited by 3
  21. 2025From Personal to Collective: On the Role of Local and Global Memory in LLM Personalizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistantscited by 0
  2. 2026Unlocking Latent Personalization in LLMscited by 0
  3. 2026MIRROR: From Imitation to Internalization in LLM Personalizationcited by 0