# MMP-Refer: Multimodal Path Retrieval-augmented LLMs For Explainable Recommendation

arXiv: https://arxiv.org/abs/2604.03666 · HTML: https://mlsanity.com/paper/2604.03666/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation.
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 24 of 24)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games](https://mlsanity.com/paper/2201.12380/) (2022)
- [Neural Collaborative Reasoning](https://mlsanity.com/paper/2005.08129/) (2020)
- [XRec: Large Language Models for Explainable Recommendation](https://mlsanity.com/paper/2406.02377/) (2024)
- [G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation](https://mlsanity.com/paper/2502.12586/) (2025)
- [Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model Adaptation](https://mlsanity.com/paper/2208.09375/) (2022)
- [PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction](https://mlsanity.com/paper/2302.12465/) (2023)
- [PerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Training](https://mlsanity.com/paper/2305.06622/) (2023)
- [HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations](https://mlsanity.com/paper/2208.09586/) (2022)
- [Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation](https://mlsanity.com/paper/2208.10692/) (2022)
- [The Problem of Coherence in Natural Language Explanations of Recommendations](https://mlsanity.com/paper/2312.11356/) (2023)

## Abstract (arXiv)

Explainable recommendations help improve the transparency and credibility of recommendation systems, and play an important role in personalized recommendation scenarios. At present, methods for explainable recommendation based on large language models(LLMs) often consider introducing collaborative information to enhance the personalization and accuracy of the model, but ignore the multimodal information in the recommendation dataset; In addition, collaborative information needs to be aligned with the semantic space of LLM. Introducing collaborative signals through retrieval paths is a good choice, but most of the existing retrieval path collection schemes use the existing Explainable GNN algorithms. Although these methods are effective, they are relatively unexplainable and not be suitable for the recommendation field. To address the above challenges, we propose MMP-Refer, a framework using MultiModal Retrieval Paths with Retrieval-augmented LLM For Explainable Recommendation. We use a sequential recommendation model based on joint residual coding to obtain multimodal embeddings, and design a heuristic search algorithm to obtain retrieval paths by multimodal embeddings; In the generation phase, we integrated a trainable lightweight collaborative adapter to map the graph encoding of interaction subgraphs to the semantic space of the LLM, as soft prompts to enhance the understanding of interaction information by the LLM. Extensive experiments have demonstrated the effectiveness of our approach. Codes and data are available at https://github.com/pxcstart/MMP-Refer.