Abstract
Peer-review–based translator training promotes reflection and collaborative critique. This study examines whether GPT5, guided by MQM-like prompts, can function as a peer-review training partner rather than a grading tool. Using translated passages from a practice group, we compared GPT5’s feedback with human evaluations of the same segments, including both negative and positive judgments. GPT5 aligned with human evaluators on 77.8% of negative flags and 88.9% of positive flags, and achieved an F1 score of 0.875 for detailed rationales supporting the flags. The results suggest that GPT5 can provide useful analyses and alternative perspectives that support learner reflection, although its occasional poor judgments indicate that it should be used as a supplementary training partner rather than a standalone evaluator.- Anthology ID:
- 2026.amta-research.4
- Volume:
[Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)](/volumes/2026.amta-research/)- Month:
- August
- Year:
- 2026
- Address:
- Québec City, Canada
- Editors:
[Eleftheria Briakou](/people/eleftheria-briakou/unverified/),[Jeremy Gwinnup](/people/jeremy-gwinnup/),[Shivali Goel](/people/shivali-goel/unverified/)- Venue:
[AMTA](/venues/amta/)- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- 42–79
- Language:
- URL:
[https://aclanthology.org/2026.amta-research.4/](https://aclanthology.org/2026.amta-research.4/)- DOI:
- Cite (ACL):
- Ming Qian and Luyi Yang. 2026. LLMs as Translator Training Partners: A Multi-Agent Approach. InProceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 42–79, Québec City, Canada. Association for Machine Translation in the Americas. - Cite (Informal):
[LLMs as Translator Training Partners: A Multi-Agent Approach](https://aclanthology.org/2026.amta-research.4/)(Qian & Yang, AMTA 2026)- PDF:
[https://aclanthology.org/2026.amta-research.4.pdf](https://aclanthology.org/2026.amta-research.4.pdf)