Exploring Multimodal Large Language Models for Next-Generation Recommendation Systems |
||
 |
 |
|
| © 2025 by IJCTT Journal | ||
| Volume-73 Issue-2 |
||
| Year of Publication : 2025 | ||
| Authors : Kailash Thiyagarajan | ||
| DOI : 10.14445/22312803/IJCTT-V73I2P108 | ||
How to Cite?
Kailash Thiyagarajan, "Exploring Multimodal Large Language Models for Next-Generation Recommendation Systems," International Journal of Computer Trends and Technology, vol. 73, no. 2, pp. 64-70, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I2P108
Abstract
Multimodal Large Language Models (MLLMs) integrate diverse data modalities—including textual descriptions, visual content, and contextual signals—into a unified framework for advanced machine learning tasks. In recommendation systems, these models offer a more comprehensive approach by combining user behavioral data, product metadata, and visual features to enhance relevance prediction. This research explores an end-to-end integration of MLLMs into recommendation pipelines, spanning from data preparation and model adaptation in the batch training phase to real-time serving for low latency inference. A modular architecture is introduced, built on a pre-trained transformer backbone with modality-specific encoders, allowing seamless fusion of multimodal inputs. Empirical evaluations on an e-commerce dataset reveal that the proposed MLLM-based recommender outperforms unimodal baselines, leading to higher recall and improved user satisfaction. Critical considerations for data alignment, scalability, and interpretability in real-world deployment are also discussed. These findings highlight the transformative potential of multimodal learning in next-generation recommendation systems.
Keywords
Multimodal large language models, Recommendation systems, Cross-modal fusion, Personalized content, Transformer-based models, Real-time inference.
Reference
[1] Yehuda Koren, Robert Bell, and Chris Volinsky, “Matrix Factorization Techniques for Recommender Systems,” Computer, vol. 42, no. 8, pp. 30-37, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Heng-Tze Cheng et al., “Wide & Deep Learning for Recommender Systems,” Proceedings of the 1st Workshop on Deep Learning for Recommender Systems (DLRS), Boston MA USA, pp. 7-10, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Huifeng Guo et al., “DeepFM: A Factorization-Machine Based Neural Network for CTR Prediction,” arXiv, pp. 1-8, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Jacob Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, pp. 4171-4186, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Alec Radford et al., “Learning Transferable Visual Models from Natural Language Supervision,” Proceedings of the 38th International Conference on Machine Learning (ICML), vol. 139, pp. 8748-8763, 2021.
[Google Scholar] [Publisher Link]
[6] Alexey Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” Proceedings of the International Conference on Learning Representations (ICLR), pp. 1-22, 2021.
[Google Scholar] [Publisher Link]
[7] Andrew Jaegle et al., “Perceiver IO: A General Architecture for Structured Inputs and Outputs,” arXiv, pp. 1-29, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
8] Jean-Baptiste Alayrac et al., “Flamingo: A Visual Language Model for Few-Shot Learning,” Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), pp. 1-21, 2022.
[Google Scholar] [Publisher Link]
[9] Liunian Harold Li et al., “VisualBERT: A Simple and Performant Baseline for Vision and Language,” arXiv, pp. 1-14, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Chen Sun et al., “VideoBERT: A Joint Model for Video and Language Representation Learning,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7464-7473, 2019.
[CrossRef] [Google Scholar] [Publisher Link]