arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.08090cs.CLcs.AIcs.LG
收藏

多语言大语言模型天然偏好低资源语言中的语言内时间敏感语义对齐

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages

Indian Institute of Technology Delhi(印度德里理工学院);Wipro Research(威普罗研究院)

Ashutosh Bajpai, Tanmoy Chakraborty

AI总结:

针对低资源语言时间推理不足,提出CLiTSSA方法及mTEMPREASON数据集,利用语言内语义对齐提升性能,在罗马尼亚语、德语和法语上超越基线。

摘要:

资源丰富语言与低资源语言在标注资源上的持续差距,仍然是大型语言模型(LLMs)面临的一个重大障碍。近期跨语言上下文学习(X-ICL)的进展,主要通过从多语言预训练Transformer中检索语义对齐的示例,已显示出缓解这一问题的潜力。然而,我们的调查揭示,LLMs天然偏好语言内语义对齐的跨语言实例,而非直接的跨语言语义对齐,且在X-ICL设置中处理时间敏感查询时存在显著差异。此类查询要求LLMs具备良好的时间推理能力,但相关进展主要集中在英语上。本研究旨在通过提升低资源语言的时间推理能力来弥合这一差距。为此,我们引入了mTEMPREASON,一个针对不同程度低资源语言的时间推理数据集,并提出了跨语言时间敏感语义对齐(CLiTSSA),一种新颖的方法,以改善这些情境下的时间推理。为促进这一点,我们构建了mTEMPREASON的扩展,包含跨语言时间查询对及其预期的语言内语义相似度分数。我们的实证证据强调了CLiTSSA相较于已建立基线的优越性能,涵盖三种语言——罗马尼亚语、德语和法语,涉及三个时间任务,并包括四个当代LLMs的多样化集合。这标志着在跨语言时间推理背景下解决资源差异问题的重要一步。

英文摘要:

The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our investigation reveals that LLMs intrinsically reward in-language semantically aligned cross-lingual instances over direct cross-lingual semantic alignments, with a pronounced disparity in handling time-sensitive queries in the X-ICL setup. Such queries demand sound temporal reasoning ability from LLMs, yet the advancements have predominantly focused on English. This study aims to bridge this gap by improving temporal reasoning capabilities in low-resource languages. To this end, we introduce mTEMPREASON, a temporal reasoning dataset aimed at the varied degrees of low-resource languages and propose Cross-Lingual Time-Sensitive Semantic Alignment (CLiTSSA), a novel method to improve temporal reasoning in these contexts. To facilitate this, we construct an extension of mTEMPREASON comprising pairs of parallel cross-language temporal queries along with their anticipated in-language semantic similarity scores. Our empirical evidence underscores the superior performance of CLiTSSA compared to established baselines across three languages -- Romanian, German, and French, encompassing three temporal tasks and including a diverse set of four contemporaneous LLMs. This marks a significant step forward in addressing resource disparity in the context of temporal reasoning across languages.

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。

↑