Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.19756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913871704358912 |
|---|---|
| author | Roll, Nathan |
| author_facet | Roll, Nathan |
| contents | Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel, parameter-efficient framework for enhancing the multilingual capabilities of LLMs. Our method learns a set of trigger tokens for each language through a gradient-based search, identifying the input query's language and selecting the corresponding trigger tokens which are prepended to the prompt during inference. We perform experiments on two ~1 billion parameter models, with evaluations on the global MMLU benchmark across fifteen typologically and resource diverse languages, demonstrating accuracy gains of 3.7%-19.9% compared to naive and translation-pipeline baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19756 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PolyPrompt: Automating Knowledge Extraction from Multilingual Language Models with Dynamic Prompt Generation Roll, Nathan Computation and Language Machine Learning Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel, parameter-efficient framework for enhancing the multilingual capabilities of LLMs. Our method learns a set of trigger tokens for each language through a gradient-based search, identifying the input query's language and selecting the corresponding trigger tokens which are prepended to the prompt during inference. We perform experiments on two ~1 billion parameter models, with evaluations on the global MMLU benchmark across fifteen typologically and resource diverse languages, demonstrating accuracy gains of 3.7%-19.9% compared to naive and translation-pipeline baselines. |
| title | PolyPrompt: Automating Knowledge Extraction from Multilingual Language Models with Dynamic Prompt Generation |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2502.19756 |