# BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages

arXiv: https://arxiv.org/abs/2608.13722 · HTML: https://mlsanity.com/paper/2608.13722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Multi30K: Multilingual English-German Image Descriptions](https://mlsanity.com/paper/1605.00459/) (2016)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [SMOL: Professionally translated parallel data for 115 under-represented languages](https://mlsanity.com/paper/2502.12301/) (2025)
- [MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Data](https://mlsanity.com/paper/2512.11074/) (2025)
- [ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages](https://mlsanity.com/paper/2512.01077/) (2025)
- [Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing](https://mlsanity.com/paper/2601.03135/) (2026)
- [NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data](https://mlsanity.com/paper/2512.12537/) (2025)
- [Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task](https://mlsanity.com/paper/2605.20626/) (2026)

## Abstract (arXiv)

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.