探索大型语言模型中的多语言探测：一项跨语言分析
Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
AI总结：
本文将LLMs的探测技术扩展至多语言语境，通过跨语言实验揭示了高低资源语言在探测准确率、层级趋势和表征相似度上的显著差异，强调了改进低资源语言建模的必要性。
摘要：
大型语言模型（LLMs）的探测技术主要集中于英语，忽视了世界上绝大多数语言。本文将这些探测方法扩展到多语言语境，研究LLMs在不同语言中的行为。我们在多个开源LLM模型上进行实验，分析多种语言的探测准确率、跨层趋势以及探测向量间的相似性。我们的主要发现揭示：（1）高资源与低资源语言间存在一致的性能差距，高资源语言获得显著更高的探测准确率；（2）不同层准确率趋势分化，高资源语言在较深层中表现出与英语类似的显著提升；（3）高资源语言间的表征相似度更高，低资源语言在彼此间及与高资源语言间均表现出较低相似度。这些结果突显了LLMs多语言能力的显著差异，并强调了对低资源语言改进建模的需求。
英文摘要：
Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the behaviors of LLMs across diverse languages. We conduct experiments on several open-source LLM models, analyzing probing accuracy, trends across layers, and similarities between probing vectors for multiple languages. Our key findings reveal: (1) a consistent performance gap between high-resource and low-resource languages, with high-resource languages achieving significantly higher probing accuracy; (2) divergent layer-wise accuracy trends, where high-resource languages show substantial improvement in deeper layers similar to English; and (3) higher representational similarities among high-resource languages, with low-resource languages demonstrating lower similarities both among themselves and with high-resource languages. These results highlight significant disparities in LLMs' multilingual capabilities and emphasize the need for improved modeling of low-resource 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。
