# Exploring Parameter-Efficient Fine-Tuning and Backtranslation for the WMT 25 General Translation Task

arXiv: https://arxiv.org/abs/2511.12109 · HTML: https://mlsanity.com/paper/2511.12109/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 2 of 2)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)

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

- [Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis](https://mlsanity.com/paper/2512.11388/) (2025)

## Abstract (arXiv)

In this paper, we explore the effectiveness of combining fine-tuning and backtranslation on a small Japanese corpus for neural machine translation. Starting from a baseline EnglishtextrightarrowJapanese model (COMET = 0.460), we first apply backtranslation (BT) using synthetic data generated from monolingual Japanese corpora, yielding a modest increase (COMET = 0.468). Next, we fine-tune (FT) the model on a genuine small parallel dataset drawn from diverse Japanese news and literary corpora, achieving a substantial jump to COMET = 0.589 when using Mistral 7B. Finally, we integrate both backtranslation and fine-tuning -- first augmenting the small dataset with BT generated examples, then adapting via FT -- which further boosts performance to COMET = 0.597. These results demonstrate that, even with limited training data, the synergistic use of backtranslation and targeted fine-tuning on Japanese corpora can significantly enhance translation quality, outperforming each technique in isolation. This approach offers a lightweight yet powerful strategy for improving low-resource language pairs.