# RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation

arXiv: https://arxiv.org/abs/2506.20817 · HTML: https://mlsanity.com/paper/2506.20817/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 25 Jun 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [Multi-Modal Self-Supervised Learning for Recommendation](https://mlsanity.com/paper/2302.10632/) (2023)
- [A Content-Driven Micro-Video Recommendation Dataset at Scale](https://mlsanity.com/paper/2309.15379/) (2023)
- [Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems](https://mlsanity.com/paper/2501.11759/) (2025)
- [MMREC: LLM Based Multi-Modal Recommender System](https://mlsanity.com/paper/2408.04211/) (2024)
- [Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models](https://mlsanity.com/paper/2402.08670/) (2024)
- [MMRec: Simplifying Multimodal Recommendation](https://mlsanity.com/paper/2302.03497/) (2023)
- [Federated Recommendation via Hybrid Retrieval Augmented Generation](https://mlsanity.com/paper/2403.04256/) (2024)
- [Recommendation with Generative Models](https://mlsanity.com/paper/2409.15173/) (2024)
- [Toward Holistic Evaluation of Recommender Systems Powered by Generative Models](https://mlsanity.com/paper/2504.06667/) (2025)
- [Graph Retrieval-Augmented LLM for Conversational Recommendation Systems](https://mlsanity.com/paper/2503.06430/) (2025)
- [Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2404.03514/) (2024)
- [Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems](https://mlsanity.com/paper/2505.05196/) (2025)
- [Ducho 2.0: Towards a More Up-to-Date Unified Framework for the Extraction of Multimodal Features in Recommendation](https://mlsanity.com/paper/2403.04503/) (2024)
- [RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation](https://mlsanity.com/paper/2309.10469/) (2023)

## Built on by (most cited first, 3 of 3)

- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Agentic Personalized Fashion Recommendation in the Age of Generative AI: Challenges, Opportunities, and Evaluation](https://mlsanity.com/paper/2508.02342/) (2025)

## Abstract (arXiv)

This paper addresses the challenge of building multimodal recommender systems for the movie domain, where sparse item metadata (e.g., title and genres) can limit retrieval quality and downstream recommendations. We introduce RAG-VisualRec, an open resource and reproducible pipeline that combines (i) LLM-generated item-side plot descriptions and (ii) trailer-derived visual (and optional audio) embeddings, supporting both retrieval-augmented generation (RAG) and collaborative-filtering style workflows. Our pipeline augments sparse metadata into richer textual signals and integrates modalities via configurable fusion strategies (e.g., PCA and CCA) before retrieval and optional LLM-based re-ranking. Beyond providing the resource, we provide a complementary analysis that increases transparency and reproducibility. In particular, we introduce LLMGenQC, a critic-based quality-control module (LLM-as-judge) that audits synthetic synopses for semantic alignment with metadata, consistency, safety, and basic sanity checks, releasing critic scores and pass/fail labels alongside the generated artifacts. We report ablation studies that quantify the impact of key design choices, including retrieval depth, fusion strategy, and user-embedding construction. Across experiments, CCA-based fusion consistently improves recall over unimodal baselines, while LLM-based re-ranking typically improves nDCG by refining top-K selection from the retrieved candidate pool, especially when textual evidence is limited. By releasing RAG-VisualRec, we enable further research on multimodal RAG recommenders, quality auditing of LLM-generated side information, and long-tail oriented evaluation protocols. All code, data, and detailed documentation are publicly available at: https://github.com/RecSys-lab/RAG-VisualRec.