HexaBee-4B:結合多語言問答與雙向監督的六語翻譯模型
HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision
HexaBee-4B 是一款由 Gemma 3 4B IT 改造、面向六種語言翻譯的模型,訓練結合多語言問答及雙向翻譯監督。在涵蓋六種語言全部 30 個方向的 36,572 個合成測試例子中,其方向宏平均 chrF++ 為 73.75,高於 Gemma 3 4B IT 的 57.11 及 Gemma 3 12B IT 的 66.83。
Published on Oct 12
Authors:
,
Abstract
Multilingual translation requires a model to preserve meaning while producing text in a requested language. We present HexaBee-4B, a translator adapted from Gemma 3 4B IT through three stages: Wikipedia continued pretraining, joint multilingual answering and answer-text translation, and bidirectional translation specialization. The intermediate stage connects two tasks through shared multilingual answers: answering a question in the requested language and translating an answer into that language. It comprises 19.46 million answering records, including 5.76 million cross-language question-answer pairs, and 10.70 million answer-text translations. The final stage uses 658,274 forward and reverse synthetic translation examples. On 36,572 synthetic test examples spanning all 30 directions among Arabic, Chinese, English, Hebrew, Persian, and Spanish, HexaBee-4B achieves direction-macro chrF++ of 73.75, compared with 57.11 for Gemma 3 4B IT and 66.83 for Gemma 3 12B IT. BLEU, TER, COMET, and a matched model-judged subset support the same overall ranking. These results demonstrate improved translation across the six-language set, with chrF++ gains in every evaluated direction over both baselines.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.16361
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.16361 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.16361 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.16361 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co