# LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning

arXiv: https://arxiv.org/abs/2406.15859 · HTML: https://mlsanity.com/paper/2406.15859/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 37 of its 61 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 30 of 37)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation](https://mlsanity.com/paper/2107.02137/) (2021)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [DKN: Deep Knowledge-Aware Network for News Recommendation](https://mlsanity.com/paper/1801.08284/) (2018)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Reinforcement Knowledge Graph Reasoning for Explainable Recommendation](https://mlsanity.com/paper/1906.05237/) (2019)
- [LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities](https://mlsanity.com/paper/2305.13168/) (2023)
- [How Powerful are K-hop Message Passing Graph Neural Networks](https://mlsanity.com/paper/2205.13328/) (2022)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [A Survey of Knowledge Enhanced Pre-trained Language Models](https://mlsanity.com/paper/2211.05994/) (2022)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Communicative Message Passing for Inductive Relation Reasoning](https://mlsanity.com/paper/2012.08911/) (2020)
- [Knowledge-Aware Language Model Pretraining](https://mlsanity.com/paper/2007.00655/) (2020)
- [Jointly Learning Explainable Rules for Recommendation with Knowledge Graph](https://mlsanity.com/paper/1903.03714/) (2019)
- [Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning](https://mlsanity.com/paper/1909.11334/) (2019)
- [GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations](https://mlsanity.com/paper/2208.04222/) (2022)

## Built on by (most cited first, 10 of 10)

- [GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation](https://mlsanity.com/paper/2503.12600/) (2025)
- [Towards Explainable Temporal User Profiling with LLMs](https://mlsanity.com/paper/2505.00886/) (2025)
- [Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications](https://mlsanity.com/paper/2510.21131/) (2025)
- [SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection](https://mlsanity.com/paper/2408.12748/) (2024)
- [ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning](https://mlsanity.com/paper/2604.07851/) (2026)
- [EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding](https://mlsanity.com/paper/2410.14276/) (2024)
- [Topic-Aware Knowledge Graph with Large Language Models for Interoperability in Recommender Systems](https://mlsanity.com/paper/2412.20163/) (2024)
- [Effectiveness of LLMs in Temporal User Profiling for Recommendation](https://mlsanity.com/paper/2511.00176/) (2025)
- [Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendation](https://mlsanity.com/paper/2504.11658/) (2025)
- [From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system](https://mlsanity.com/paper/2509.18980/) (2025)

## Abstract (arXiv)

Recommender systems are pivotal in enhancing user experiences across various web applications by analyzing the complicated relationships between users and items. Knowledge graphs(KGs) have been widely used to enhance the performance of recommender systems. However, KGs are known to be noisy and incomplete, which are hard to provide reliable explanations for recommendation results. An explainable recommender system is crucial for the product development and subsequent decision-making. To address these challenges, we introduce a novel recommender that synergies Large Language Models (LLMs) and KGs to enhance the recommendation and provide interpretable results. Specifically, we first harness the power of LLMs to augment KG reconstruction. LLMs comprehend and decompose user reviews into new triples that are added into KG. In this way, we can enrich KGs with explainable paths that express user preferences. To enhance the recommendation on augmented KGs, we introduce a novel subgraph reasoning module that effectively measures the importance of nodes and discovers reasoning for recommendation. Finally, these reasoning paths are fed into the LLMs to generate interpretable explanations of the recommendation results. Our approach significantly enhances both the effectiveness and interpretability of recommender systems, especially in cross-selling scenarios where traditional methods falter. The effectiveness of our approach has been rigorously tested on four open real-world datasets, with our methods demonstrating a superior performance over contemporary state-of-the-art techniques by an average improvement of 12%. The application of our model in a multinational engineering and technology company cross-selling recommendation system further underscores its practical utility and potential to redefine recommendation practices through improved accuracy and user trust.