Augmenting Vision-Language Retrieval: The Role of Multimodal LLMs as Synthetic Data Generators.

@inproceedings{bell-2025-augmenting, author = {Aidan Bell and James Gore and Behrooz Mansouri}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Augmenting Vision-Language Retrieval: The Role of Multimodal LLMs as Synthetic Data Generators}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {3050--3054}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3730167}, doi = {https://doi.org/10.1145/3726302.3730167} }