GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation

2026/08/01 by Yong Wang, Hongliang Sun, Jinlan Liu +4
Computer Science · #cs.IR

paper · pdf

18 pages, 2 figures

arxiv created 2026/08/01 · arxiv updated 2026/08/04

Abstract

Large language models (LLMs) offer new opportunities for recommendation by interpreting item descriptions, user instructions, and external knowledge through natural-language prompts. However, existing graph-augmented LLM recommenders often use knowledge graphs mainly as prompt-level evidence, leaving ranking decisions weakly constrained by structured user-item relations. This is problematic for next-item recommendation, where the model must compare candidates under the same user context while preserving temporal preference, collaborative signals, and attribute matches. To address this issue, we propose GARDRec, a Graph-grounded Adaptive Reasoning and Decision-aware Recommendation framework for LLM-based next-item ranking. GARDRec constructs semantic-structural item representations from textual node features and graph propagation, derives personalized graph contexts from temporally weighted histories and first-order neighborhoods, and aligns graph-derived representations with a frozen LLM through continuous multimodal prompts. Explicit interaction and matching features are injected through late-stage decision branches, while inter-candidate attention and restricted generative likelihood support final ranking. Experiments on three public benchmarks with multiple LLM backbones show that GARDRec generally improves candidate-ranking performance over representative baselines. Ablation and diagnostic analyses verify the contributions of graph projection, neighborhood retrieval, explicit decision features, ranking loss, and generative calibration.

Citations

• ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
• KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation
• LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
• G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation
• Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
• RecLM: Recommendation Instruction Tuning
• LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
• CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
• Retrieval-Augmented Generation for AI-Generated Content: A Survey
• Let Your Graph Do the Talking: Encoding Structured Data for LLMs
• RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
• LLMRec: Large Language Models with Graph Augmentation for Recommendation
• Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering
• ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
• Lost in the Middle: How Language Models Use Long Contexts
• Large Language Models are Zero-Shot Rankers for Recommender Systems
• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach
• Is ChatGPT a Good Recommender? A Preliminary Study
• Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Self-Attentive Sequential Recommendation
• Neural Collaborative Filtering