大语言模型真的能仅凭一本语法书学会翻译一种极低资源语言吗？
Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
AI总结：
本研究探究LLM能否仅凭语法书翻译极低资源语言，发现翻译能力主要来自平行示例而非语法解释，并强调任务适配数据的重要性。
摘要：
极低资源（XLR）语言缺乏用于训练NLP模型的大量语料，这促使研究者利用所有可用资源，如词典和语法书。Tanzer等人（2024）的“从一本书进行机器翻译”（Machine Translation from One Book）研究表明，向长上下文大语言模型（LLM）提示一本语法书即可实现英语-卡拉马语（Kalamang）的翻译，卡拉马语是一种LLM未见过的XLR语言——这是语言学帮助NLP任务的一个值得注意的案例。我们探究了这种翻译能力的来源，发现几乎所有改进都源于书中的平行示例，而非语法解释。我们在尼泊尔语（Nepali）和瓜拉尼语（Guarani）这两种已见的低资源语言上得到了类似结果，并且仅通过微调一个编码器-解码器翻译模型，我们就达到了与使用语法书的LLM相当的性能。随后，我们通过测试两项语言学任务——语法性判断和词汇预测——来考察语法书在哪些方面有帮助，并通过引入一种类型学特征提示（typological feature prompt）来探索何种语法知识有用，该提示在这些更相关的任务上取得了领先结果。因此，我们强调任务适配数据对XLR语言的重要性：翻译任务需要平行示例，语言学任务需要语法数据。由于我们没有发现长上下文LLM能有效利用语法解释进行XLR翻译的证据，我们得出结论：对于翻译等多语言XLR任务的数据收集，应优先集中于平行数据而非语言学描述。
英文摘要：
Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et al., 2024) suggests that prompting long-context LLMs with one grammar book enables English-Kalamang translation, an XLR language unseen by LLMs - a noteworthy case of linguistics helping an NLP task. We investigate the source of this translation ability, finding almost all improvements stem from the book's parallel examples rather than its grammatical explanations. We find similar results for Nepali and Guarani, seen low-resource languages, and we achieve performance comparable to an LLM with a grammar book by simply fine-tuning an encoder-decoder translation model. We then investigate where grammar books help by testing two linguistic tasks, grammaticality judgment and gloss prediction, and we explore what kind of grammatical knowledge helps by introducing a typological feature prompt that achieves leading results on these more relevant tasks. We thus emphasise the importance of task-appropriate data for XLR languages: parallel examples for translation, and grammatical data for linguistic tasks. As we find no evidence that long-context LLMs can make effective use of grammatical explanations for XLR translation, we conclude data collection for multilingual XLR tasks such as translation is best focused on parallel data over linguistic description.
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。
