Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
This work addresses a specific problem in NLP for researchers and practitioners by improving probing methods for multilingual sequence labeling, though it is incremental as it builds on existing prompting strategies.
The paper tackles the challenge of probing multilingual linguistic structure knowledge in large language models (LLMs) for sequence labeling tasks by introducing a decomposed prompting approach, which outperforms iterative prompting baselines in efficacy and efficiency across 38 languages in zero- and few-shot settings.
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.