@inproceedings{wang-etal-2026-glossagen,
    title = "{G}lossa{G}en: Making Academic Translation Smarter with Glossing",
    author = "Wang, Zixiao  and
      Zhang, Duzhen  and
      Zhang, Juntian  and
      Liu, Yuhan  and
      Li, Guoming  and
      Wu, Haolun  and
      Song, Le  and
      Chen, Xiuying",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.952/",
    pages = "19077--19095",
    ISBN = "979-8-89176-395-1",
    abstract = "When reading foreign-language literature, non-native users often face significant challenges. Existing traditional machine translation systems tend to obscure or mistranslate key terminology, while paraphrasing aimed at lay readers often oversimplifies it, thereby hindering their ability to master domain-specific technical vocabulary. To bridge this gap, we first define a novel task, Glossing-Oriented Academic Translation (GOAT), which aims to produce translations dynamically adapted to a reader{'}s academic proficiency, or level. We then propose GlossaGen, a comprehensive framework to address this task. GlossaGen features two key innovations: a multi-agent data synthesis pipeline that leverages academic personas to automatically generate a large-scale, structured dataset with level-specific explanations; and a novel training strategy based on dynamic adapter merging, which balances task generalization with user-level specialization by combining a ``generalist'' adapter with a fine-grained ``expert'' one. We evaluate GlossaGen on our synthesized benchmark, where results from automatic metrics, large language model (LLM)-based assessments, and human evaluations consistently demonstrate that our approach achieves higher scores than strong baselines across most metrics. Our framework provides a scalable pathway to enhance the comprehensibility of scientific literature for non-native readers, delivering more accurate translations accompanied by pedagogically sound, level-specific term explanations, and we release our code and data to facilitate further research."
}