Metraipolis › archive › dc_0141457d563f

UvA-MT's Participation in the WMT26 General Translation Shared Task — arXiv:2610.27852

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27852
License (as archived)
CC0-1.0
Archived
2026-10-21T07:09:03.224Z
SHA-256 of the archived text
eb04548e0d35b9771595300654ed18b2dc4bc4bd2d59993081250b9b5e4145ec
Stable URL of this page
https://metraipolis.com/documento/dc_0141457d563f

How to cite

UvA-MT's Participation in the WMT26 General Translation Shared Task — arXiv:2610.27852 — arXiv (en), https://arxiv.org/abs/2610.27852 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0141457d563f (Metraipolis archive dc_0141457d563f, sha256 eb04548e0d35b9771595300654ed18b2dc4bc4bd2d59993081250b9b5e4145ec)
BibTeX
@misc{dc0141457d563f,
  title = {UvA-MT's Participation in the WMT26 General Translation Shared Task — arXiv:2610.27852},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27852},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0141457d563f; sha256 eb04548e0d35b9771595300654ed18b2dc4bc4bd2d59993081250b9b5e4145ec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27852. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents UvA-MT's submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source segment, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidate via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Combined, these two strategies form our WMT26 submission.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.27852 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:58.133Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).