IRB-MT at WMT25 Translation Task: A Simple Agentic System Using an Off-the-Shelf LLM

Grubišić, Ivan; Korenčić, Damir (2025) IRB-MT at WMT25 Translation Task: A Simple Agentic System Using an Off-the-Shelf LLM. In: Haddow, Barry; Kocmi, Tom; Koehn, Philipp; Monz, Christof, (eds.) Proceedings of the Tenth Conference on Machine Translation. Suzhou, CHina, Association for Computational Linguistics (ACL), pp. 753-764 .

PDF - Published Version - article Available under License Creative Commons Attribution. Download (255kB)

Abstract

Large Language Models (LLMs) have been demonstrated to achieve state-of-art results on machine translation. LLM-based translation systems usually rely on model adaptation and fine-tuning, requiring datasets and compute. The goal of our team’s participation in the “General Machine Translation” and “Multilingual” tasks of WMT25 was to evaluate the translation effectiveness of a resource-efficient solution consisting of a smaller off-the-shelf LLM coupled with a self-refine agentic workflow. Our approach requires a high-quality multilingual LLM capable of instruction following. We select Gemma3-12B among several candidates using the pretrained translation metric MetricX-24 and a small development dataset. WMT25 automatic evaluations place our solution in the mid tier of all WMT25 systems, and also demonstrate that it can perform competitively for approximately 16% of language pairs.

Item Type:	Conference or workshop item published in conference proceedings (UNSPECIFIED)
Uncontrolled Keywords:	machine translation; natural language processing; large language models; multi-agent system
Subjects:	TECHNICAL SCIENCES > Computing > Artificial Intelligence
Divisions:	Division of Electronics
Depositing User:	Ivan Grubišić
Date Deposited:	14 Jan 2026 15:03
URI:	http://fulir.irb.hr/id/eprint/10840
DOI:	10.18653/v1/2025.wmt-1.51

Actions (login required)

View Item