2026 · conference
QUERY-SYNERGY: Leveraging High-Resource Languages for Improving Retrieval Performance Across Multiple Languages
Seongtae Hong, Jungseob Lee, Hyeonseok Moon, Seungyoon Lee, Youngjoon Jang, Heuiseok Lim†
Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)
Abstract
Multilingual embedding models often exhibit uneven representational quality, heavily favoring high-resource languages like English. However, conventional retrieval systems that rely exclusively on source-language queries fail to exploit the superior semantic expressiveness of these high-resource subspaces. To address this, we propose Query-Synergy, a training-free approach to improving retrieval performance using multilingual embeddings. Our method utilizes additional queries in English to complement source language queries and integrates similarity scores from both queries, effectively enhancing retrieval performance. We evaluate our approach across five languages (Arabic, Chinese, Greek, Thai, and Turkish) using four multilingual embedding models on two datasets. Our experiments show that this approach outperforms conventional source query retrieval methods, achieving superior nDCG scores across various configurations and translation settings. These results confirm that Query-Synergy is a simple yet effective method for retrieval across multiple languages.
Motivation
<!-- Replace the sentence below with your personal motivation for this work. -->Personal motivation for this work will be added here.
Notes
<!-- Optional: add contributions, behind-the-scenes notes, talks, code, or media links. -->BibTeX
@inproceedings{2026-query-synergy-leveraging-high-resource-languages,
title = {QUERY-SYNERGY: Leveraging High-Resource Languages for Improving Retrieval Performance Across Multiple Languages},
author = {Seongtae Hong and Jungseob Lee and Hyeonseok Moon and Seungyoon Lee and Youngjoon Jang and Heuiseok Lim},
booktitle = {Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)},
year = {2026},
month = {7},
pages = {44-51},
abstract = {Multilingual embedding models often exhibit uneven representational quality, heavily favoring high-resource languages like English. However, conventional retrieval systems that rely exclusively on source-language queries fail to exploit the superior semantic expressiveness of these high-resource subspaces. To address this, we propose Query-Synergy, a training-free approach to improving retrieval performance using multilingual embeddings. Our method utilizes additional queries in English to complement source language queries and integrates similarity scores from both queries, effectively enhancing retrieval performance. We evaluate our approach across five languages (Arabic, Chinese, Greek, Thai, and Turkish) using four multilingual embedding models on two datasets. Our experiments show that this approach outperforms conventional source query retrieval methods, achieving superior nDCG scores across various configurations and translation settings. These results confirm that Query-Synergy is a simple yet effective method for retrieval across multiple languages.},
url = {https://aclanthology.org/2026.mellm-1.4/}
}