# Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs

arXiv: https://arxiv.org/abs/2507.16672 · HTML: https://mlsanity.com/paper/2507.16672/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [SCORE: Story Coherence and Retrieval Enhancement for AI Narratives](https://mlsanity.com/paper/2503.23512/) (2025)
- [A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product](https://mlsanity.com/paper/2403.08511/) (2024)
- [Research on Splicing Image Detection Algorithms Based on Natural Image Statistical Characteristics](https://mlsanity.com/paper/2404.16296/) (2024)
- [Research on reinforcement learning based warehouse robot navigation algorithm in complex warehouse layout](https://mlsanity.com/paper/2411.06128/) (2024)
- [Enhanced Recommendation Combining Collaborative Filtering and Large Language Models](https://mlsanity.com/paper/2412.18713/) (2024)
- [Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy](https://mlsanity.com/paper/2504.08751/) (2025)
- [Personalized Risks and Regulatory Strategies of Large Language Models in Digital Advertising](https://mlsanity.com/paper/2505.04665/) (2025)
- [User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data](https://mlsanity.com/paper/2505.06305/) (2025)
- [Machine Learning-Based Prediction of Metal-Organic Framework Materials: A Comparative Analysis of Multiple Models](https://mlsanity.com/paper/2507.04493/) (2025)
- [Psychological Health Knowledge-Enhanced LLM-based Social Network Crisis Intervention Text Transfer Recognition Method](https://mlsanity.com/paper/2504.07983/) (2025)
- [II-NVM: Enhancing Map Accuracy and Consistency with Normal Vector-Assisted Mapping](https://mlsanity.com/paper/2504.08204/) (2025)
- [CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image Reconstruction](https://mlsanity.com/paper/2505.12203/) (2025)
- [LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion](https://mlsanity.com/paper/2505.23809/) (2025)
- [Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks](https://mlsanity.com/paper/2506.05873/) (2025)
- [Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models](https://mlsanity.com/paper/2506.06336/) (2025)
- [Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems](https://mlsanity.com/paper/2506.17551/) (2025)
- [Research on feature fusion and multimodal patent text based on graph attention network](https://mlsanity.com/paper/2505.20188/) (2025)
- [A Deep Learning Algorithm Based on CNN-LSTM Framework for Predicting Cancer Drug Sales Volume](https://mlsanity.com/paper/2506.21927/) (2025)
- [Regression and Forecasting of U.S. Stock Returns Based on LSTM](https://mlsanity.com/paper/2502.05210/) (2025)
- [SemIRNet: A Semantic Irony Recognition Network for Multimodal Sarcasm Detection](https://mlsanity.com/paper/2506.14791/) (2025)

## Built on by (most cited first, 5 of 5)

- [RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders](https://mlsanity.com/paper/2508.05289/) (2025)
- [Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM](https://mlsanity.com/paper/2509.13179/) (2025)
- [Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users](https://mlsanity.com/paper/2509.09066/) (2025)
- [Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms](https://mlsanity.com/paper/2509.04751/) (2025)
- [Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences](https://mlsanity.com/paper/2606.07629/) (2026)

## Abstract (arXiv)

Generative, explainable, and flexible recommender systems, derived using Large Language Models (LLM) are promising and poorly adapted to the cold-start user situation, where there is little to no history of interaction. The current solutions i.e. supervised fine-tuning and collaborative filtering are dense-user-item focused and would be expensive to maintain and update. This paper introduces a meta-learning framework, that can be used to perform parameter-efficient prompt-tuning, to effectively personalize LLM-based recommender systems quickly at cold-start. The model learns soft prompt embeddings with first-order (Reptile) and second-order (MAML) optimization by treating each of the users as the tasks. As augmentations to the input tokens, these learnable vectors are the differentiable control variables that represent user behavioral priors. The prompts are meta-optimized through episodic sampling, inner-loop adaptation, and outer-loop generalization. On MovieLens-1M, Amazon Reviews, and Recbole, we can see that our adaptive model outperforms strong baselines in NDCG@10, HR@10, and MRR, and it runs in real-time (i.e., below 300 ms) on consumer GPUs. Zero-history personalization is also supported by this scalable solution, and its 275 ms rate of adaptation allows successful real-time risk profiling of financial systems by shortening detection latency and improving payment network stability. Crucially, the 275 ms adaptation capability can enable real-time risk profiling for financial institutions, reducing systemic vulnerability detection latency significantly versus traditional compliance checks. By preventing contagion in payment networks (e.g., Fedwire), the framework strengthens national financial infrastructure resilience.