arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.04792cs.CLcs.LG
收藏

打破语言壁垒:在多语言大语言模型应用中直接推理能否优于预翻译?

Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?

Verily Life Sciences(Verily生命科学公司);Google Research(谷歌研究院)

Yotam Intrator, Matan Halfon, Roman Goldenberg, Reut Tsarfaty, Matan Eyal, Ehud Rivlin, Yossi Matias, Natalia Aizenberg

AI总结:

该研究针对大语言模型预翻译的局限,基于PaLM2模型开展跨108种语言、6个基准的研究,证实直接推理在多数语言下优于预翻译,为多语言应用提供更高效方案。

摘要:

大语言模型在多语言应用中具备巨大潜力。然而,其预训练过程以英语为核心的固有偏差催生了预翻译的普遍做法,即在推理前将非英语输入翻译成英语,这会带来流程复杂度与信息损失问题。本研究针对在多语言任务中表现优异的PaLM2模型(Anil等人,2023),重新评估了预翻译的必要性。我们开展了覆盖108种语言、6个不同基准的全面研究,其中包含此前同类研究未纳入的开放式生成任务。研究结果挑战了以往研究确立的预翻译范式,凸显了PaLM2中直接推理的优势:具体而言,PaLM2-L在108种语言中的94种里表现始终优于预翻译。这些发现为更高效、更有效的多语言应用铺平了道路,缓解了预翻译带来的限制,释放了语言本真性。

英文摘要:

Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating non-English inputs to English before inference, leading to complexity and information loss. This study re-evaluates the need for pre-translation in the context of PaLM2 models (Anil et al., 2023), which have been established as highly performant in multilingual tasks. We offer a comprehensive investigation across 108 languages and 6 diverse benchmarks, including open-end generative tasks, which were excluded from previous similar studies. Our findings challenge the pre-translation paradigm established in prior research, highlighting the advantages of direct inference in PaLM2. Specifically, PaLM2-L consistently outperforms pre-translation in 94 out of 108 languages. These findings pave the way for more efficient and effective multilingual applications, alleviating the limitations associated with pre-translation and unlocking linguistic authenticity.

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。

↑