paper-with-me

홈 › Papers

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

2026-03-22 · Abdul-Salem Beibitkhan arxiv

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning, technical, and culturally grounded categories, we evaluate 2,000 responses on accuracy, fluency, and completeness. We find a consistent performance gap of 13.8-16.7 percentage points between English and low-resource language conditions, with models maintaining surface-level fluency while producing significantly less accurate content. Cross-lingual transfer-prompting models to reason in English before translating back-yields selective gains for bilingual architectures (+2.2pp to +4.3pp) but provides no benefit to English-dominant models. Our results demonstrate that current LLMs systematically underserve low-resource language communities, and that effective mitigation strategies are architecture-dependent rather than universal.

📄 PDF Abstract BibTeX arXiv:2603.21036

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual Transfer

Similar Papers 제목 키워드 기반

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity

2024-03-08 · Sho Hoshino, Akihiko Kato, Soichiro Murakami, Peinan Zhang

Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large…

Cross-Lingual TransferData AugmentationMachine TranslationNatural Language Inference+5

No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages

2024-11-06 · Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, Kilichbek Haydarov 외

Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced som…

Cross-Lingual TransferDiversity

Can Monolingual Pretrained Models Help Cross-Lingual Classification?

2019-11-10 · Asian Chapter of the Association for Computational Linguistics 2020 · Zewen Chi, Li Dong, Furu Wei, Xian-Ling Mao 외

Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind …

ClassificationCross-Lingual TransferGeneral Classification

The Less the Merrier? Investigating Language Representation in Multilingual Models

2023-10-20 · Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Jugal Kalita

Multilingual Language Models offer a way to incorporate multiple languages in one model and utilize cross-language transfer learning to improve performance for different Natural Language Processing (NLP) tasks. Despite p…

named-entity-recognitionNamed Entity RecognitionText GenerationTransfer Learning

Enhancing Cross-lingual Transfer by Manifold Mixup

2022-05-09 · ICLR 2022 4 · Huiyun Yang, Huadong Chen, Hao Zhou, Lei LI

Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances. However, the performance of target languages still lags far behind the …

Cross-Lingual Transfer