缓解英语到罗马尼亚语机器翻译中的性别偏见
原标题：Mitigating Gender Bias in English to Romanian Machine Translation
AI 摘要
该论文提出了一种混合流水线，结合基于大语言模型的性别分类与标签感知的神经机器翻译，以缓解英语到罗马尼亚语机器翻译中的性别偏见。系统通过微调的LLM检测目标词的性别并插入提示标签，再由微调的Transformer模型生成形态正确的罗马尼亚语翻译。在WinoMT和WinoGender基准上，性别准确率相比基线系统提升了超过40个百分点。这是首个显式解决并评估英罗翻译性别偏见的方法。
正文节选
Mitigating Gender Bias in English to Romanian Machine Translation Abstract A hybrid pipeline combining LLM gender classification with tag-aware neural translation improves gender accuracy in English-to-Romanian machine translation. 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 reinf