Model Releases
BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages
arXiv:2608.13722v1 Announce Type: new Abstract: This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieva
arXiv:2608.13722v1 Announce Type: new Abstract: This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.
Related
- Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
- Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages
- CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script
- Adapting Large Language Models to a Low-Resource Agglutinative Language: A Comparative Study of LoRA and QLoRA for Bashkir
Source: arXiv cs.CL | 2026-08-17