# Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task

arXiv: https://arxiv.org/abs/2605.20626 · HTML: https://mlsanity.com/paper/2605.20626/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 5 of 5)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models](https://mlsanity.com/paper/2305.17406/) (2023)
- [Sheffield's Submission to the AmericasNLP Shared Task on Machine Translation into Indigenous Languages](https://mlsanity.com/paper/2306.09830/) (2023)
- [MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Data](https://mlsanity.com/paper/2512.11074/) (2025)
- [Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing](https://mlsanity.com/paper/2601.03135/) (2026)

## Built on by (most cited first, 1 of 1)

- [BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages](https://mlsanity.com/paper/2608.13722/) (2026)

## Abstract (arXiv)

We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our two-stage pipeline generates a Spanish intermediate caption with Qwen2.5-VL, then produces the target-language caption using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. We achieve 164.1%, 131.7%, and 122.6% improvements over the shared task baseline for Bribri, Guaran'i, and Orizaba Nahuatl captioning, respectively, in our dev set evaluation and maintain >150% improvements for the Bribri and Orizaba Nahuatl languages in the test set evaluation. We find retrieval is highly language-dependent, beneficial only for large, in-domain corpora, and that synthetic data augmentation accounts for around 28 chrF++ of the dev set Guaran'i performance gain. Our submission is the overall winner of the shared task, placing second out of five finalist submissions in human evaluations of target-language captions.