注意包容性差距：使用mGeNTE进行多语言性别中立翻译评估
Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE
AI总结：
本文引入专家策划的资源mGeNTE，利用指令遵循语言模型对多语言性别中立翻译进行系统性评估，发现模型虽能识别中立需求但难以持续生成中立翻译，并通过可解释性分析揭示了其内部动态。
摘要：
避免传播不当的（二元）性别推断和默认男性语言，依然是迈向包容性多语言技术的关键挑战，特别是在翻译成具有大量性别形态变化的语言时。性别中立翻译（GNT）代表了一种实现跨语言更公平交流的语言策略。然而，关于GNT的研究仅局限于少数资源和语言对。为了弥补这一差距，我们引入了专家策划的资源mGeNTE，并利用它对最先进的指令遵循语言模型（LMs）进行了首次系统性的包容性翻译多语言评估。在en-es/de/it/el上的实验表明，尽管模型能够识别何时适合保持中立，但无法持续生成中立翻译，这限制了其可用性。为了探究这一行为，我们通过可解释性分析丰富了评估，识别了与任务相关的特征，并为基于LM的GNT的内部动态提供了初步见解。
英文摘要：
Avoiding the propagation of undue (binary) gender inferences and default masculine language remains a key challenge towards inclusive multilingual technologies, particularly when translating into languages with extensive gendered morphology. Gender-neutral translation (GNT) represents a linguistic strategy towards fairer communication across languages. However, research on GNT is limited to a few resources and language pairs. To address this gap, we introduce mGeNTE, an expert-curated resource, and use it to conduct the first systematic multilingual evaluation of inclusive translation with state-of-the-art instruction-following language models (LMs). Experiments on en-es/de/it/el reveal that while models can recognize when neutrality is appropriate, they cannot consistently produce neutral translations, limiting their usability. To probe this behavior, we enrich our evaluation with interpretability analyses that identify task-relevant features and offer initial insights into the internal dynamics of LM-based GNT.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
