mlsanityData to 14 Oct 2026

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs

arXiv 2601.12034 ↗First posted 17 Jan 2026cs.CL cs.IRcited by 3

Not on the map. Why?

Abstract (arXiv)

Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this limitation, we propose the Prompt-level User Migration Adapter (PUMA), a lightweight framework to efficiently migrate personalized prompts across incompatible models. PUMA utilizes a parameter-efficient adapter to bridge the semantic gap, combined with a group-based user selection strategy to significantly reduce training costs. Experiments on three large-scale datasets show our method matches or even surpasses the performance of retraining from scratch, reducing computational cost by up to 98%. The framework demonstrates strong generalization across diverse model architectures and robustness in advanced scenarios like chained and aggregated migrations, offering a practical path for the sustainable evolution of personalized AI by decoupling user assets from the underlying models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 17 Jan 2026.

Builds on

20 of 32 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2022Beyond neural scaling laws: beating power law scaling via data pruningcited by 528
  7. 2019Selection via Proxy: Efficient Data Selection for Deep Learningcited by 339
  8. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 280
  9. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  10. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
  11. 2024Large Language Models for Education: A Survey and Outlookcited by 188
  12. 2022Coverage-centric Coreset Selection for High Pruning Ratescited by 117
8 more
  1. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 116
  2. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 100
  3. 2022Personalized Prompt Learning for Explainable Recommendationcited by 79
  4. 2022Adaptive Second Order Coresets for Data-efficient Machine Learningcited by 60
  5. 2024Large Language Models are Learnable Planners for Long-Term Recommendationcited by 24
  6. 2024SPRec: Self-Play to Debias LLM-based Recommendationcited by 18
  7. 2025Process-Supervised LLM Recommenders via Flow-guided Tuningcited by 10
  8. 2025Fine-grained List-wise Alignment for Generative Medication Recommendationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendationcited by 2
  2. 2026Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMscited by 1
  3. 2026Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendationcited by 0