英译印地语中的文化保真度：性别可恢复性的保持-流畅性前沿
Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverability
AI总结：
研究英译印地语中性别信息的保持问题，提出两种推理时干预方法（SAR和PAR），在保持性别可恢复性与流畅性之间取得平衡。
摘要：
生成式翻译系统是文化技术，因为它们决定如何在特定文化的语法系统中呈现具有社会意义的线索。我们研究成功文化翻译的一个具体概念：当英语源文本明确编码性别时，英译印地语应保持该线索的可恢复性，除非源文本本身存在歧义。我们在涵盖十二个类别的37,345个实例基准上评估了这一标准，并显示五个系统经常通过作格和敬语结构消除性别。然后，我们引入了两种机制感知的推理时干预。第一种是源感知重排序器（SAR），倾向于避免性别中立句法的候选。第二种是现象感知重排序器（PAR），即使在作格句法存在的情况下，也通过目标词汇标记保持性别。在GPT-4o-mini和Sarvam上，PAR将目标子集准确率分别从11.07%提高到54.47%，从15.99%提高到49.66%。人工评估显示，PAR将性别保持率从10.3%提高到81.3%，但平均流畅度从4.36降至3.37。这些发现将两种干预置于保持和流畅性的前沿，而不是支持单一的解决方案，并展示了文化定位的生成如何在保真度、流畅性和风格自然性之间需要明确的权衡。
英文摘要：
Generative translation systems are cultural technologies because they decide how socially meaningful cues are rendered within culturally specific grammatical systems. We study one concrete notion of successful cultural translation: when an English source explicitly encodes gender, an English-to-Hindi translation should preserve the recoverability of that cue unless the source itself is ambiguous. We evaluate this criterion on a 37,345-instance benchmark spanning twelve categories and show that five systems frequently erase gender through ergative and honorific constructions. We then introduce two mechanism-aware inference-time interventions. The first, the Source-Aware Reranker (SAR), prefers candidates that avoid gender-neutralizing syntax. The second, the Phenomenon-Aware Reranker (PAR), preserves gender through targeted lexical marking even when ergative syntax remains. Across GPT-4o-mini and Sarvam, PAR improves target-subset accuracy from 11.07% to 54.47% and from 15.99% to 49.66%, respectively. Human evaluation shows that PAR increases gender preservation from 10.3% to 81.3%, but reduces mean fluency from 4.36 to 3.37. These findings place the two interventions on a preservation and fluency frontier rather than supporting a single dominant solution, and show how culturally situated generation can require explicit tradeoffs among fidelity, fluency, and stylistic naturalness.
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。
