# X-Reflect: Cross-Reflection Prompting for Multimodal Recommendation

arXiv: https://arxiv.org/abs/2408.15172 · HTML: https://mlsanity.com/paper/2408.15172/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs](https://mlsanity.com/paper/2401.02582/) (2024)
- [Cross-Batch Negative Sampling for Training Two-Tower Recommenders](https://mlsanity.com/paper/2110.15154/) (2021)
- [TagGPT: Large Language Models are Zero-shot Multimodal Taggers](https://mlsanity.com/paper/2304.03022/) (2023)
- [Understanding Political Polarization via Jointly Modeling Users, Connections and Multimodal Contents on Heterogeneous Graphs](https://mlsanity.com/paper/2201.05946/) (2022)

## Built on by (most cited first, 6 of 6)

- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Personalized Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2412.02142/) (2024)
- [Large Language Model Enhanced Recommender Systems: A Survey](https://mlsanity.com/paper/2412.13432/) (2024)
- [EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Models](https://mlsanity.com/paper/2508.15721/) (2025)
- [Multimodal Music Recommendation System using LLMs](https://mlsanity.com/paper/2606.00125/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have been shown to enhance the effectiveness of enriching item descriptions, thereby improving the accuracy of recommendation systems. However, most existing approaches either rely on text-only prompting or employ basic multimodal strategies that do not fully exploit the complementary information available from both textual and visual modalities. This paper introduces a novel framework, Cross-Reflection Prompting, termed X-Reflect, designed to address these limitations by prompting Multimodal Large Language Models (MLLMs) to explicitly identify and reconcile supportive and conflicting information between text and images. By capturing nuanced insights from both modalities, this approach generates more comprehensive and contextually rich item representations. Extensive experiments conducted on two widely used benchmarks demonstrate that our method outperforms existing prompting baselines in downstream recommendation accuracy. Furthermore, we identify a U-shaped relationship between text-image dissimilarity and recommendation performance, suggesting the benefit of applying multimodal prompting selectively. To support efficient real-time inference, we also introduce X-Reflect-keyword, a lightweight variant that summarizes image content using keywords and replaces the base model with a smaller backbone, achieving nearly 50% reduction in input length while maintaining competitive performance. This work underscores the importance of integrating multimodal information and presents an effective solution for improving item understanding in multimodal recommendation systems.