mlsanityData to 7 Oct 2026

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

arXiv 2601.06362 ↗First posted 10 Jan 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user preferences. To address this challenge, we propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style. PsPLUG also allows us to tune personalization strength at inference time. Our experiments show that explicit style instructions can diminish personalization in existing methods, whereas PsPLUG better preserves user preferences while providing precise control over the balance between personalization and style adherence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 51 references that are in the map. First posted on arXiv 10 Jan 2026.

Builds on

42 of 51 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  10. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  11. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  12. 2024Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Modelscited by 431
30 more
  1. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  2. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  3. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 271
  4. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  5. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  6. 2018Training Millions of Personalized Dialogue Agentscited by 126
  7. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 98
  8. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  9. 2024LongLaMP: A Benchmark for Personalized Long-form Text Generationcited by 91
  10. 2024RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculturecited by 80
  11. 2024Aligning LLM Agents by Learning Latent Preference from User Editscited by 66
  12. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  13. 2024PAD: Personalized Alignment of LLMs at Decoding-Timecited by 58
  14. 2019Generating Personalized Recipes from Historical User Preferencescited by 52
  15. 2022Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generationcited by 47
  16. 2024Personalized Large Language Modelscited by 44
  17. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 44
  18. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  19. 2024Customizing Language Models with Instance-wise LoRA for Sequential Recommendationcited by 32
  20. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  21. 2025Language Model Personalization via Reward Factorizationcited by 27
  22. 2018Personalized Language Model for Query Auto-Completioncited by 25
  23. 2023RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generationcited by 25
  24. 2019Towards Controllable and Personalized Review Generationcited by 24
  25. 2025LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimizationcited by 24
  26. 2024Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Modelscited by 20
  27. 2024Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendationcited by 16
  28. 2025Drift: Decoding-time Personalized Alignments with Implicit User Preferencescited by 13
  29. 2024Step-Back Profiling: Distilling User History for Personalized Scientific Writingcited by 9
  30. 2026CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generationcited by 2

Built on by

Not cited yet.