Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
On the map: Retrieval-augmented generation → Multimodal RAG
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.
Key facts. Cited by 1 paper 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.
Builds on
5 of 15 references.
References · 5
- 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
- 2023Enhancing Translation for Indigenous Languages: Experiments with Multilingual Modelscited by 4
- 2023Sheffield's Submission to the AmericasNLP Shared Task on Machine Translation into Indigenous Languagescited by 4
- 2025MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Datacited by 4
- 2026Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessingcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrieval
- 2025CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning
- 2025RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
- 2024CIC: A Framework for Culturally-Aware Image Captioning
- 2024Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning
- 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
- 2025CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation
- 2023Retrieval-augmented Image Captioning