An Efficient LLM-based Evolutional Recommendation with Locate-Forget-Update Paradigm
Preprint
Abstract
Nowadays, Large Language Models (LLMs) have shown exceptional performance in sequential recommendations, and the adoption of LLM-based recommender systems (LLMRec) is becoming increasingly widespread in existing e-commerce platforms. Despite the impressive performance, the constant high volume of new user-item interactions makes it difficult to adapt to the evolution of user preference over time, especially for LLM-based recommender systems. The challenge arises from the large number of parameters in LLMs, which makes traditional evolution methods (i.e., Re-training or Fine-tuning) impractical. Specifically, Re-training with all interactions results in prohibitively high computational costs. On the other hand, fine-tuning with only new interactions leads to preference forgetting among inactive users, ultimately compromising overall performance. To tackle this problem, we propose EvoRec, an efficient Locate-Forget-Update framework designed for LLM-based recommender systems to model the evolution of user preferences. EvoRec identifies a small set of parameters associated with preference changes and updates them precisely, thereby saving computational resources while maintaining strong recommendation performance. Notably, the modified parameters account for only 30\% of LoRA adapter parameters, with no additional parameters introduced. Extensive experiments on two real-world datasets demonstrate that, compared to existing methods, EvoRec not only efficiently evolves LLMRec to adapt to the preferences of active users, but also preserves the interests of inactive users from being disturbed during evolution.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings2025
- RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k RecommendationACM Transactions on Information Systems, 2025
- Enhancing ID-based Recommendation with Large Language ModelsACM Transactions on Information Systems, 2025
- Federated Semantic Learning for Privacy-preserving Cross-domain RecommendationACM Transactions on Information Systems, 2025
- Semantic-enhanced Co-attention Prompt Learning for Non-overlapping Cross-Domain RecommendationACM Transactions on Information Systems, 2025
- Large Language Models for Generative Recommendation: A Survey and Visionary Discussions2024
- Customizing Language Models with Instance-wise LoRA for Sequential Recommendation2024
- Locating and Editing Factual Associations in GPT2022
- Exploiting Positional Information for Session-Based RecommendationACM Transactions on Information Systems, 2021
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017