M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets.

@inproceedings{palmer-2026-mdaq, author = {Christopher R. Palmer and Chunguang Zhao and Djoerd Hiemstra and Li Zhang and Christopher R. Palmer and Chunguang Zhao and Charles L. A. Clarke and Yilun Liu and Shunshun Peng and Yuanchang Luo and Boxing Chen and Claudia Hauff and Charles L. A. Clarke and Yilun Liu and Pufan Zeng and Shimin Tao and Zhejian Zhang and Jordi Turmo and Mengmeng Yang and Minggui He and Daimeng Wei and Leif Azzopardi and Shunshun Peng and Yuanchang Luo and Jordi Turmo and Mengmeng Yang and Minggui He and Shimin Tao and Zhejian Zhang and Kwok-Yan Lam and Weibin Meng and Jordi Turmo and Mengmeng Yang and Minggui He and Kwok-Yan Lam and Weibin Meng and Song Xu and Chen Liu and Hongxia Ma and Djoerd Hiemstra and Li Zhang and Boxing Chen and Claudia Hauff and Daimeng Wei and Leif Azzopardi}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {4361--4366}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809946}, doi = {https://doi.org/10.1145/3805712.3809946} }