Metraipolis › archive › dc_2b94c06b286d
Mitigating Gender Bias in English to Romanian Machine Translation — arXiv:2608.08606
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08606
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:04.601Z
- SHA-256 of the archived text
a313eec3affc7c9657c4025cd19a75dd95c30865a3453f0eea35e47261b878b8- Stable URL of this page
https://metraipolis.com/documento/dc_2b94c06b286d
How to cite
Mitigating Gender Bias in English to Romanian Machine Translation — arXiv:2608.08606 — arXiv (en), https://arxiv.org/abs/2608.08606 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b94c06b286d (Metraipolis archive dc_2b94c06b286d, sha256 a313eec3affc7c9657c4025cd19a75dd95c30865a3453f0eea35e47261b878b8)
BibTeX
@misc{dc2b94c06b286d,
title = {Mitigating Gender Bias in English to Romanian Machine Translation — arXiv:2608.08606},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08606},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b94c06b286d; sha256 a313eec3affc7c9657c4025cd19a75dd95c30865a3453f0eea35e47261b878b8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08606. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a gendered target language such as Romanian. This bias results in translations that default to masculine forms or reinforce gender stereotypes. We propose a hybrid pipeline to mitigate this issue by combining large language model (LLM)-based gender classification with neural machine translation (NMT). Our system uses a fine-tuned LLM to detect the intended gender of target words in English sentences and insert inline gender hint tags. These tagged sentences are then passed to a Transformer model fine-tuned to generate morphologically correct Romanian translations. To support this, we introduce three novel datasets for gender disambiguation and translation. Our approach improves gender accuracy on the WinoMT and WinoGender benchmarks by over 40 percentage points compared to a baseline MT system. This is the first method to explicitly address and evaluate gender bias in English-Romanian MT using both LLM inference and tag-aware translation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.08606 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:49:41.863Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).