Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915600534601728 |
|---|---|
| author | Nie, Ercong Yuan, Shuzhou Ma, Bolei Schmid, Helmut Färber, Michael Kreuter, Frauke Schütze, Hinrich |
| author_facet | Nie, Ercong Yuan, Shuzhou Ma, Bolei Schmid, Helmut Färber, Michael Kreuter, Frauke Schütze, Hinrich |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models Nie, Ercong Yuan, Shuzhou Ma, Bolei Schmid, Helmut Färber, Michael Kreuter, Frauke Schütze, Hinrich Computation and Language 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. |
| title | Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.18397 |