@InProceedings{dhawan-EtAl:2026:wmt,
  author    = {Dhawan, Aashish  and  Driggers-Ellis, Christopher William  and  Kasinets, Dzmitry  and  Grant, Christan  and  Wang, Zhe},
  title     = {gators: BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {2118--2130},
  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.},
  url       = {https://aclanthology.org/2026.wmt-1.150}
}