cs.CLNov 8, 2026

Saidzoda-CA-EmbeddingGemma-300M: One Small Embedder for Tajik, Kazakh, Uzbek and Kyrgyz

Authors: Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov, Abubakr Abdullozoda, Amin Jalilov, Jonibek Kishvarov, Rahmonali Sharipov, Mariyamkhon Shodyeva

Organizations: Saidzoda AI Lab, Saidzoda Engineering Company, Dushanbe, Tajikistan

Abstract

The small open embedder EmbeddingGemma-300M, used as released, finds the right passage first for only 51.7% to 60.8% of Belebele questions in Tajik, Kazakh, Uzbek and Kyrgyz. We present Saidzoda-CA-EmbeddingGemma-300M, one model for all four languages. It is our Tajik fine-tune of EmbeddingGemma-300M, trained for one more epoch on 279,904 pairs: questions in Kazakh, Uzbek and Kyrgyz that our own language model wrote about source passages, a Tajik refresher, and English and Russian replay. On Belebele, recall@1 rises by 14.4 to 26.0 points in each language, to between 75.2% and 77.7%. Against single-language models trained with the same settings, the one model stays within 2.8 points at recall@1 in Kazakh, Uzbek and Tajik, with overlapping recall@10 intervals, though it also had more training. It keeps the Tajik law recall@10 of its starting point (92.2 against 92.4) but loses 4.4 points of law recall@1. A model trained on one of these languages also improves the others on Belebele, but less than training on them. The model still trails the 560M XLM-RoBERTa embedders on Kazakh, Uzbek and Kyrgyz Belebele: the better of multilingual-e5-large-instruct and BGE-M3, used as released, is 9.4 to 10.2 points ahead at recall@1. Our scores of those released models agree with the published MTEB results within 2.4 points. Russian and English recall@1 fall by 3.0 and 4.2 points.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Saidzoda-Kazakh-EmbeddingGemma-300M: How Far One Epoch of Generated Questions Takes a Small Kazakh Embedder

    Nov 12, 2026Tohir Saidzoda, Madina Abdusalomzoda, Abubakr Abdullozoda +3Text Embedding ModelsDense Retrieval

  2. Saidzoda-Tajik-EmbeddingGemma-300M: Knowing Every Letter Is Not Reading Tajik

    Nov 8, 2026Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5Text Embedding ModelsInformation Retrieval

  3. Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval

    Oct 31, 2026Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5Text Embedding ModelsDense Retrieval