Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages

arXiv:2403.06018v1 Announce Type: cross
Abstract: Large pre-trained language models (PLMs) are at the forefront of advances in Natural Language Processing. One widespread use case of PLMs is "prompting" - or in-context learning - where a user provides a description of a task and some completed examples of the task to a PLM as context before prompting the PLM to perform the task on a new example. Only the largest, most capable PLMs are able to perform in-context learning effectively, and …

abstract advances arxiv case context cross-lingual cs.ai cs.cl cs.lg examples few-shot in-context learning language language models language processing languages large language large language models low natural natural language natural language processing processing prompting transfer type