Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models

Understand

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.