Tuning-Free LLM Can Build A Strong Recommender Under Sparse Connectivity And Knowledge Gap Via Extracting Intent

TL;DR

This paper introduces IKGR, a tuning-free, intent-centric knowledge graph recommender leveraging LLMs and GNNs, effectively addressing sparsity and cold-start issues with improved accuracy and efficiency.

Contribution

The paper presents a novel intent knowledge graph framework built with a tuning-free LLM pipeline, enhancing recommendation quality for sparse and cold-start scenarios.

Findings

Outperforms strong baselines on public and enterprise datasets.

Effectively handles cold-start and long-tail items.

Maintains low latency with a lightweight GNN layer.

Abstract

Recent advances in recommendation with large language models (LLMs) often rely on either commonsense augmentation at the item-category level or implicit intent modeling on existing knowledge graphs. However, such approaches struggle to capture grounded user intents and to handle sparsity and cold-start scenarios. In this work, we present LLM-based Intent Knowledge Graph Recommender (IKGR), a novel framework that constructs an intent-centric knowledge graph where both users and items are explicitly linked to intent nodes extracted by a tuning-free, RAG-guided LLM pipeline. By grounding intents in external knowledge sources and user profiles, IKGR canonically represents what a user seeks and what an item satisfies as first-class entities. To alleviate sparsity, we further introduce a mutual-intent connectivity densification strategy, which shortens semantic paths between users and long-tail items without requiring cross-graph fusion. Finally, a lightweight GNN layer is employed on top of the intent-enhanced graph to produce recommendation signals with low latency. Extensive experiments on public and enterprise datasets demonstrate that IKGR consistently outperforms strong baselines, particularly on cold-start and long-tail slices, while remaining efficient through a fully offline LLM pipeline.