Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

LLMs Are Few-Shot In-Context Low-Resource Language Learners

Domaine:

natural language processing

Type de record:

paper
Créateur:
CahLovFun
Hôte:avatar
In-context learning (ICL) empowers large language models (LLMs) to perform diverse tasks in underrepresented languages using only short in-context information, offering a crucial avenue for narrowing the gap between high-resource and low-resource languages. Nonetheless, there is only a handful of works explored ICL for low-resource languages with most of them focusing on relatively high-resource languages, such as French and Spanish. In this work, we extensively study ICL and its cross-lingual variation (X-ICL) on 25 low-resource and 7 relatively higher-resource languages. Our study not only assesses the effectiveness of ICL with LLMs in low-resource languages but also identifies the shortcomings of in-context label alignment, and introduces a more effective alternative: query alignment. Moreover, we provide valuable insights into various facets of ICL for low-resource languages. Our study concludes the significance of few-shot in-context information on enhancing the low-resource understanding quality of LLMs through semantically relevant information by closing the language gap in the target language and aligning the semantics between the targeted low-resource and the high-resource language that the model is proficient in. Our work highlights the importance of advancing ICL research, particularly for low-resource languages. Our code is publicly released at github.com

Visit

arxiv.org

Tasks

language modelingtransfer learning

Tags

Computation and LanguageArtificial Intelligence

Similaires

Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource LanguagesVisually grounded few-shot word learning in low-resource settingsmGPT: Few-Shot Learners Go MultilingualPerformance comparison of projection-based cross-lingual NER and few-shot multilingual LLMs on XTREME-R low-resource languagesCross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource Languageskobeoseijnr/Few-Shot-Sentiment-Learning-with-Synthetic-Augmentation-in-Low-Resource-Settings

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

Large pre-trained language models (PLMs) are at the forefront of advances in Natural Language Proces

Visually grounded few-shot word learning in low-resource settings

We propose a visually grounded speech model that learns new words and their visual depictions from j

mGPT: Few-Shot Learners Go Multilingual

Recent studies report that autoregressive language models can successfully solve many NLP tasks via zero- and few-shot learning paradigms, which opens up new possibilities for using the pre-trained language models. This paper introduces two autoregressive GPT-like

Performance comparison of projection-based cross-lingual NER and few-shot multilingual LLMs on XTREME-R low-resource languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Cross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

kobeoseijnr/Few-Shot-Sentiment-Learning-with-Synthetic-Augmentation-in-Low-Resource-Settings

Few Shot Sentiment Learning with Synthetic Augmentation in Low Resource Settings # Few-Shot Sentime