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

ACL ARR 2024 April Submission355 Authors

Abstract:

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.

Paper Type: Short

Research Area: Multilingualism and Cross-Lingual NLP

Research Area Keywords: Multilingual Evaluation, Multilinugal Large Language Models, Prompting, part-of-speech tagging, few-shot learning

Contribution Types: Model analysis & interpretability

Languages Studied: English,Chinese,etc.

Submission Number: 355