@inproceedings{jang-etal-2026-improving,
    title = "Improving {K}orean-{E}nglish Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging",
    author = "Jang, Youngjoon  and
      Son, Junyoung  and
      Lee, Taemin  and
      Hong, Seongtae  and
      Moon, Hyeonseok  and
      Lee, Seungyoon  and
      Matteson, Andrew  and
      Lim, Heuiseok",
    editor = "Huang, Kaiyu  and
      Mo, Fengran  and
      Chen, Pinzhen  and
      Jiang, Meng",
    booktitle = "Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models ({M}e{LLM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.mellm-1.3/",
    pages = "30--43",
    ISBN = "979-8-89176-430-9",
    abstract = "With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training data composition on CLIR and Mono-Lingual Information Retrieval (Mono-IR) performance remains underexplored. To investigate this data-centric aspect, we construct linguistically parallel Korean-English datasets and train multilingual retrieval models with various language combinations. Our experiments reveal that the language composition of training data significantly influence IR performance, exhibiting important inter-lingual correlations: Using specific language pairs improves CLIR performance, while declines Mono-IR performance. Our work demonstrates that simple weight-averaged model merging can effectively mitigate this trade-off, achieving strong CLIR results while preserving Mono-IR capabilities. Our findings highlight the effects of linguistic configuration of training data on both CLIR and Mono-IR, and present model merging as a viable strategy to optimize performance across these tasks."
}