@inproceedings{fernandes-2026-usp,
    title = "{USP} at {A}mericas{NLP} 2026 Shared Task: Culturally-Aware Image Captioning for Indigenous Languages via Vision-Language Models and Fine-Tuned Neural Machine Translation",
    author = "Fernandes, Rafael",
    editor = "Mager, Manuel  and
      Ebrahimi, Abteen  and
      Bui, Minh Duc  and
      Pugh, Robert  and
      Oncevay, Arturo  and
      Chiruzzo, Luis  and
      Solano, Rolando Coto  and
      Rijhwani, Shruti  and
      Von Der Wense, Katharina",
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.americasnlp-6.25/",
    pages = "264--271",
    ISBN = "979-8-89176-415-6",
    abstract = "We describe the USP system for the AmericasNLP 2026 Shared Task on Culturally Relevant Image Captioning for Indigenous Languages, covering Guaran{\'i} (grn), Maya Yucateco (yua), Nahuatl (nah), Wix{\'a}rika (hch), and Bribri (bzd). We propose a two-stage cascade: Qwen3-VL-8B-Instruct (Bai et al., 2025) generates Spanish captions via language-specific cultural prompts; language-specific fine-tuned NLLB-200-distilled-600M (NLLB Team et al., 2022) models then translate them into each target language. We train on AmericasNLP 2023 data (Ebrahimi et al., 2023) augmented with public parallel corpora. Our system achieves competitive results, including 3rd place in Guaran{\'i} human evaluation (2.41/5.0) and 5th in Bribri (1.09/5.0) among 8 teams. We also report that NLLB-200-distilled-600M silently lacks vocabulary entries for Bribri and Maya Yucateco, producing English output without error."
}