@inproceedings{huang-etal-2026-generative,
    title = "Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization",
    author = "Huang, Jie  and
      Wang, Junjie  and
      Liao, Xin  and
      Jiang, Ziyou  and
      Wang, Wenshuo  and
      Li, Shoubin  and
      Wang, Qing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.632/",
    pages = "12972--12986",
    ISBN = "979-8-89176-395-1",
    abstract = "Generative Retrieval (GR) has emerged as a promising text-to-image paradigm, yet it suffers from limited semantic discriminability, alignment bias, and closed-set restrictions. To address these challenges, we propose SIGMA, a novel framework for Semantic Internalization for Generative Multimodal Alignment. SIGMA constructs multi-granularity hierarchical identifiers to ensure unique, semantically consistent image representations. We further introduce a progressive semantic internalization training strategy augmented with semantic soft labels, which captures fine-grained text-image affinities and enables inductive identifier assignment for unseen samples realizing open-set dynamic indexing capabilities. Experiments on the Flickr30K and MS-COCO datasets demonstrate that SIGMA outperforms state-of-the-art baselines, achieving average Recall@1, Recall@5, and Recall@10 improvements of 10.65{\%}, 8.50{\%}, and 7.00{\%}, respectively."
}