GlossMATE: Multi-Agent Translator Explanations for Glosses

Changbing Yang, Patrick Littell, Gabriel Bernier-Colborne, Yanfei Lu, Mengzhe Geng


Abstract
This paper introduces GlossMATE, a multi-agent critique-and-judge system that translates the gloss line in Interlinear Glossed Text (IGT) into fluent English using Large Language Models (LLMs). GlossMATE integrates linguist-provided resources (e.g., gloss-tag explanations, lexicon entries, curated IGT) with in-context learning and a multi-agent critique-and-judge procedure that iteratively evaluates and refines candidate translations. Our experiments show that leveraging analogous examples, explicit linguistic explanations, and collaborative agent interactions can enhance translation quality across several low-resource and polysynthetic languages. We also incorporate human linguists into the critique loop for selected languages. Case studies on three Indigenous languages further demonstrate the complementary strengths of human-in-the-loop feedback and multi-agent reasoning for language documentation tasks.
Anthology ID:
2026.lrec-1.709
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
9018–9029
Language:
External URL:
https://lrec.elra.info/lrec2026-main-709
DOI:
10.63317/5bhwdv5gcjqz
Bibkey:
Cite (ACL):
Changbing Yang, Patrick Littell, Gabriel Bernier-Colborne, Yanfei Lu, and Mengzhe Geng. 2026. GlossMATE: Multi-Agent Translator Explanations for Glosses. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9018–9029, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
GlossMATE: Multi-Agent Translator Explanations for Glosses (Yang et al., LREC 2026)
Copy Citation: