@article{knowledgecompletesthevisionamultimodalen, title = {Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning}, author = {Xiaoxing You and Qiang Huang and Lingyu Li and Chi Zhang and Xiaopeng Liu and Min Zhang and Jun Yu}, year = {2025}, eprint = {2511.21002}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.21002}, }