Elamur Research⌕
☰
home / papers / 2026 / GlossMATE: Multi-Agent Translator Explanations for Glosses

GlossMATE: Multi-Agent Translator Explanations for Glosses

Summary

Interlinear Glossed Text (IGT) pairs morpheme-level glosses with a free translation. Many documentation projects now produce glosses automatically through morphological analyzers and verb conjugators, at a scale no person could translate by hand. Dense gloss strings are hard for learners and community members to read. Hand-coded gloss-to-English converters are slow to build and break whenever glossing conventions change.

GlossMATE reverses the usual IGT task and uses LLMs to turn the gloss line into readable English. A translator model receives linguist-made resources in its prompt: gloss-tag explanations, lexicon entries and retrieved IGT examples for in-context learning. A critic agent then reviews candidate translations, and a judge agent decides on the refined output. Human linguists can also join the critique step.

Experiments on several low-resource and polysynthetic languages suggest that similar examples, explicit tag explanations and agent collaboration all raise translation quality. Case studies on three Indigenous languages of Canada show that expert feedback and multi-agent reasoning complement each other. This offers a cheaper, sturdier way to produce learner-friendly materials.

Key points

  • Task direction: the system translates the gloss line into the free translation. Most earlier IGT research went the other way, predicting segmentations and glosses.
  • Motivation: the conjugator of Kazantseva et al. (2018) generates about 2.5 million forms. Its rule-based gloss-to-English script reportedly took 3–6 person-months and needed constant revision.
  • Pipeline: Translator → Critic → Judge, guided by linguists' explanations and suggestions. In one example, a Michif subjunctive conjunct form is corrected so that it is rendered as an "if/when" clause.
  • Few-shot selection: the paper also tests how the choice and number of retrieved few-shot examples affect quality. Its bibliography cites Sentence-BERT, Gemma 3 and Qwen2.5, which points to embedding-based retrieval and open LLMs, but this is not confirmed in the excerpt.
  • Missing results: the supplied text omits the data and results sections, so specific scores and the full language list are not reported here.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5bhwdv5gcjqz

@inproceedings{yang2026glossmate,
  title = {{GlossMATE: Multi-Agent Translator Explanations for Glosses}},
  author = {Yang, Changbing and Littell, Patrick and Bernier-Colborne, Gabriel and Lu, Yanfei and Geng, Mengzhe},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5bhwdv5gcjqz},
  url = {https://doi.org/10.63317/5bhwdv5gcjqz}
}

References

35 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Seth Aycock, David Stap, Di Wu, Christof Monz, and Khalil Sima’an. 2025. Can llms really learn to translate a low-resource language from one grammar book? In ICLR. find
  2. LLaMA3-8B Gemma3-12B 12.77 35.32 0.689 14.75 42.66 0.774 13.60 37.88 0.731 34.11 50.50 0.707 7.26 38.07 0.636 29.56 40.74 0.716 67.54 78.89 0.912 53.10 66.30 0.879 3.29 22.71 0.488 3.88 22.67 0.356 6.91 30.19 0.593 5.97 30.59 0.586 5.66 34.65 0.558 6.79 27.67 0.600 3.72 15.86 0.312 12.96 36.98 0.652… find
  3. Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi, Desmond Elliott, Raquel Fernández, Albert Gatt, Esam Ghaleb, Mario Giulianelli, Michael Hanna, Alexander Koller, et al. 2025. Llms instead of human judges? a large scale empirical study across 20 nlp evaluation tasks. In The 63rd Annual Meetin… find our card
  4. Andrew Michael Bean, Simeon Hellsten, Harry Mayne, Jabez Magomere, Ethan A Chi, Ryan Andrew Chi, Scott A. Hale, and Hannah Rose Kirk. 2024. LINGOLY: A benchmark of olympiad-level linguistic reasoning puzzles in low resource and extinct languages. In The Thirty-eight Conference on Neural Information… find
  5. Samuel Cahyawijaya, Holy Lovenia, and Pascale Fung. 2024. LLMs are few-shot in-context low-resource language learners. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 405–… find
  6. Yujia Chen. 2025. Autoreview: An llm-based multi-agent system for security issue-oriented code review. In Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, pages 1022–1024. find
  7. Fineen Davis, Eddie Antonio Santos, and Heather Souter. 2021. On the computational modelling of michif verbal morphology. In Conference of the European Chapter of the Association for Computational Linguistics. find
  8. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2024. Improving factuality and reasoning in language models through multiagent debate. In Forty-first international conference on machine learning. find our card
  9. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783. find
  10. Michael Ginn, Mans Hulden, and Alexis Palmer. 2024. Can we teach language models to gloss endangered languages? In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5861–5876, Miami, Florida, USA. Association for Computational Linguistics. find
  11. Michael Ginn, Sarah Moeller, Alexis Palmer, Anna Stacey, Garrett Nicolai, Mans Hulden, and Miikka Silfverberg. 2023. Findings of the SIGMOR-PHON 2023 shared task on interlinear glossing. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology,… find
  12. Leander Girrbach. 2023. Tü-CL at SIGMORPHON 2023: Straight-through gradient estimation for hard attention. In Proceedings of the 20th SIG-MORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 171–185, Toronto, Canada. Association for Computational Linguistics. find
  13. Atticus Harrigan, Katherine Schmirler, Antti Arppe, Lene Antonsen, Trond Trosterud, and Arok Wolvengrey. 2017. Learning from the computational modelling of plains cree verbs. Morphology, 27. find
  14. Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Duygu Ataman, and Lonneke Van Der Plas. 2025. Evaluating morphological compositional generalization in large language models. In Proceedings of the 2025 Conference of the Nations of the Amer… find
  15. Anna Kazantseva, Owennatekha Brian Maracle, Ronkwe’tiyóhstha Josiah Maracle, and Aidan Pine. 2018. Kawennón:nis: the wordmaker for Kanyen’kéha. In Proceedings of the Workshop on Computational Modeling of Polysynthetic Languages, pages 53–64, Santa Fe, New Mexico, USA. Association for Computational L… find
  16. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th Symposium on Operating Systems Principles, pages 611–626. find
  17. Qintong Li, Leyang Cui, Lingpeng Kong, and Wei Bi. 2023. Collaborative evaluation: Exploring the synergy of large language models and humans for open-ended generation evaluation. find
  18. Patrick Littell, Darlene Stewart, Fineen Davis, Aidan Pine, and Roland Kuhn. 2024. Gramble: A tabular programming language for collaborative linguistic modeling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 202… find
  19. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. G-eval: NLG evaluation using gpt-4 with better human alignment. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2511–2522, Singapore. Association for Computational Lin… find
  20. Hongyuan Lu, Haoran Yang, Haoyang Huang, Dongdong Zhang, Wai Lam, and Furu Wei. 2024a. Chain-of-dictionary prompting elicits translation in large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 958–976, Miami, Florida, USA. Associatio… find
  21. Yanfei Lu, Patrick Littell, and Keren Rice. 2024b. Empowering Oneida language revitalization: Development of an Oneida verb conjugator. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5757–5767, Torin… find
  22. Jeffrey Micher. 2017. Improving coverage of an Inuktitut morphological analyzer using a segmental recurrent neural network. In Proceedings of the 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 101–106, Honolulu. Association for Computational Linguistics. find
  23. Sarah Moeller and Mans Hulden. 2018. Automatic glossing in a low-resource setting for language documentation. In Proceedings of the Workshop on Computational Modeling of Polysynthetic Languages, pages 84–93, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  24. Anssi Moisio, Mathias Creutz, and Mikko Kurimo. 2023. Evaluating morphological generalisation in machine translation by distribution-based compositionality assessment. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 738–751, Tórshavn, Faroe Islands. Univer… find
  25. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,… find
  26. Wei Tao, Yucheng Zhou, Yanlin Wang, Wenqiang Zhang, Hongyu Zhang, and Yu Cheng. 2024. Magis: Llm-based multi-agent framework for github issue resolution. Advances in Neural Information Processing Systems, 37:51963–51993. find
  27. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, et al. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. find
  28. Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, and Shingo Takamatsu. 2025. Talk structurally, act hierarchically: A collaborative framework for llm multi-agent systems. arXiv preprint arXiv:2502.11098. — [arXiv:2502.11098](https://arxiv.org/abs/2502.11098) find
  29. Adam Wiemerslage, Miikka Silfverberg, Changbing Yang, Arya McCarthy, Garrett Nicolai, Eliana Colunga, and Katharina Kann. 2022. Morphological processing of low-resource languages: Where we are and what’s next. In Findings of the Association for Computational Linguistics: ACL 2022, pages 988–1007, Du… find
  30. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei… find
  31. Changbing Yang, Franklin Ma, Freda Shi, and Jian Zhu. 2025. LingGym: How far are LLMs from thinking like field linguists? In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 1314–1340, Suzhou, China. Association for Computational Linguistics. find
  32. Changbing Yang, Garrett Nicolai, and Miikka Silfverberg. 2024b. Multiple sources are better than one: Incorporating external knowledge in low-resource glossing. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4537–4552, Miami, Florida, USA. Associatio… find
  33. Kexun Zhang, Yee Choi, Zhenqiao Song, Taiqi He, William Yang Wang, and Lei Li. 2024. Hire a linguist!: Learning endangered languages in LLMs with in-context linguistic descriptions. In Findings of the Association for Computational Linguistics: ACL 2024, pages 15654–15669, Bangkok, Thailand. Associat… find
  34. Xingyuan Zhao, Satoru Ozaki, Antonios Anastasopoulos, Graham Neubig, and Lori Levin. 2020. Automatic interlinear glossing for under-resourced languages leveraging translations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5397–5408, Barcelona, Spain (Online… find
  35. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems, 36:46595– 46623. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yang-2026-glossmate-multi-agent-translator-explanations/