Laniqo at WMT25 General Translation Task: Self-Improved and Retrieval-Augmented Translation
Kamil Guttmann, Zofia Rostek, Adrian Charkiewicz, Antoni Solarski, Mikołaj Pokrywka, Artur Nowakowski
Abstract
This work describes Laniqo’s submission to the constrained track of the WMT25 General MT Task. We participated in 11 translation directions. Our approach combines several techniques: fine-tuning the EuroLLM-9B-Instruct model using Contrastive Preference Optimization on a synthetic dataset, applying Retrieval-Augmented Translation with human-translated data, implementing Quality-Aware Decoding, and performing postprocessing of translations with a rule-based algorithm. We analyze the contribution of each method and report improvements at every stage of our pipeline.- Anthology ID:
- 2025.wmt-1.54
- Volume:
- Proceedings of the Tenth Conference on Machine Translation
- Month:
- November
- Year:
- 2025
- Address:
- Suzhou, China
- Editors:
- Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 778–788
- Language:
- URL:
- https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.54/
- DOI:
- Cite (ACL):
- Kamil Guttmann, Zofia Rostek, Adrian Charkiewicz, Antoni Solarski, Mikołaj Pokrywka, and Artur Nowakowski. 2025. Laniqo at WMT25 General Translation Task: Self-Improved and Retrieval-Augmented Translation. In Proceedings of the Tenth Conference on Machine Translation, pages 778–788, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- Laniqo at WMT25 General Translation Task: Self-Improved and Retrieval-Augmented Translation (Guttmann et al., WMT 2025)
- PDF:
- https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.54.pdf