Training-Free LLM-Based Recommendation with Post-LLM Item Refinement Using Collaborative Signals

2026-08-20

AI Summary

为解决LLM生成用户兴趣过于宽泛的问题，提出CoRRe框架，通过后LLM阶段引入协同过滤信号优化项目表示，提高推荐精度。

Abstract

Large language models (LLMs) have shown promise for training-free recommendation, but LLM-generated user interests are often too broad for fine-grained item retrieval. Existing methods incorporate collaborative filtering (CF) signals in a pre-LLM manner through candidate reranking or prompt augmentation, yielding limited gains. We propose CoRRe, a training-free recommendation framework with a post-LLM paradigm that injects CF signals into LLM-generated item representations, which are later matched with LLM-generated user interests for ranking. Specifically, CoRRe refines the directions of item embeddings using an item-item co-purchase graph and their magnitudes using item popularity. Experiments on real-world datasets show that CoRRe consistently outperforms existing training-free methods and achieves competitive or superior performance compared with training-based methods, without requiring any model training or task-specific fine-tuning.

Problem

• Large Language Models
• Training-Free Recommendation
• Collaborative Filtering
• Item Retrieval

Innovation

• Training-Free Recommendation
• Post-LLM Item Refinement
• Collaborative Filtering Signals
• Item Embedding Refinement