分解提示:探究大语言模型中的多语言语言结构知识
Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
AI总结:
本文提出分解提示方法,将序列标注任务拆分为逐词元提示,在38种语言的词性标注上验证其优于迭代提示基线,并揭示多语言提示下的语言知识迁移规律。
摘要:
探究大语言模型(LLMs)中关于语言结构的多语言知识,通常被描述为序列标注任务,在当前的文本到文本提示策略中面临保持输出模板的挑战。为解决这一问题,我们引入了一种用于序列标注任务的分解提示方法。与单一的文本到文本提示不同,我们的提示方法为输入句子的每个词元生成一个单独的提示,询问其语言标签。我们在包含38种语言的Universal Dependencies词性标注数据集上测试了我们的方法,使用了以英语为中心和多语言的大语言模型。我们的研究结果表明,在零样本和少样本设置下,分解提示在效果和效率上都超过了迭代提示基线。此外,我们对以英语为中心的大语言模型的多语言性能分析,为通过多语言提示实现语言知识迁移提供了见解。
英文摘要:
Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-text prompting strategies. To solve this, we introduce a decomposed prompting approach for sequence labeling tasks. Diverging from the single text-to-text prompt, our prompt method generates for each token of the input sentence an individual prompt which asks for its linguistic label. We test our method on the Universal Dependencies part-of-speech tagging dataset for 38 languages, using both English-centric and multilingual LLMs. Our findings show that decomposed prompting surpasses the iterative prompting baseline in efficacy and efficiency under zero- and few-shot settings. Moreover, our analysis of multilingual performance of English-centric LLMs yields insights into the transferability of linguistic knowledge via multilingual prompting.
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。