Saved in:
Bibliographic Details
Main Authors: Azizi, Vahid, Koochaki, Fatemeh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.07449
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910995680591872
author Azizi, Vahid
Koochaki, Fatemeh
author_facet Azizi, Vahid
Koochaki, Fatemeh
contents Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks. However, existing RAG approaches predominantly rely on flat, similarity-based retrieval that fails to leverage the rich relational structure inherent in user-item interactions. We introduce LlamaRec-LKG-RAG, a novel single-pass, end-to-end trainable framework that integrates personalized knowledge graph context into LLM-based recommendation ranking. Our approach extends the LlamaRec architecture by incorporating a lightweight user preference module that dynamically identifies salient relation paths within a heterogeneous knowledge graph constructed from user behavior and item metadata. These personalized subgraphs are seamlessly integrated into prompts for a fine-tuned Llama-2 model, enabling efficient and interpretable recommendations through a unified inference step. Comprehensive experiments on ML-100K and Amazon Beauty datasets demonstrate consistent and significant improvements over LlamaRec across key ranking metrics (MRR, NDCG, Recall). LlamaRec-LKG-RAG demonstrates the critical value of structured reasoning in LLM-based recommendations and establishes a foundation for scalable, knowledge-aware personalization in next-generation recommender systems. Code is available at~\href{https://github.com/VahidAz/LlamaRec-LKG-RAG}{repository}.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
Azizi, Vahid
Koochaki, Fatemeh
Information Retrieval
Artificial Intelligence
Computation and Language
Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks. However, existing RAG approaches predominantly rely on flat, similarity-based retrieval that fails to leverage the rich relational structure inherent in user-item interactions. We introduce LlamaRec-LKG-RAG, a novel single-pass, end-to-end trainable framework that integrates personalized knowledge graph context into LLM-based recommendation ranking. Our approach extends the LlamaRec architecture by incorporating a lightweight user preference module that dynamically identifies salient relation paths within a heterogeneous knowledge graph constructed from user behavior and item metadata. These personalized subgraphs are seamlessly integrated into prompts for a fine-tuned Llama-2 model, enabling efficient and interpretable recommendations through a unified inference step. Comprehensive experiments on ML-100K and Amazon Beauty datasets demonstrate consistent and significant improvements over LlamaRec across key ranking metrics (MRR, NDCG, Recall). LlamaRec-LKG-RAG demonstrates the critical value of structured reasoning in LLM-based recommendations and establishes a foundation for scalable, knowledge-aware personalization in next-generation recommender systems. Code is available at~\href{https://github.com/VahidAz/LlamaRec-LKG-RAG}{repository}.
title LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2506.07449