SEA-LION: Southeast Asian Languages in One Network
Paper
•
2504.05747
•
Published
LLMs for "Low Training Data Languages"
-
-
Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings
Paper • 2408.02237 • Published -
A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs
Paper • 2406.17377 • Published -
Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
Paper • 2306.11372 • Published -
A Benchmark for Learning to Translate a New Language from One Grammar Book
Paper • 2309.16575 • Published • 1 -
Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
Paper • 2409.19151 • Published -
Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus
Paper • 2410.14815 • Published • 1 -
LLaMA Beyond English: An Empirical Study on Language Capability Transfer
Paper • 2401.01055 • Published • 56 -
PersianMind: A Cross-Lingual Persian-English Large Language Model
Paper • 2401.06466 • Published • 5 -
MaLA-500: Massive Language Adaptation of Large Language Models
Paper • 2401.13303 • Published • 13 -
CroissantLLM: A Truly Bilingual French-English Language Model
Paper • 2402.00786 • Published • 27 -
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Paper • 2401.16380 • Published • 51 -
Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages
Paper • 2406.12739 • Published -
TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese
Paper • 2401.16640 • Published • 9 -
Lugha-Llama: Adapting Large Language Models for African Languages
Paper • 2504.06536 • Published -
SambaLingo: Teaching Large Language Models New Languages
Paper • 2404.05829 • Published • 13 -
Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
Paper • 2412.13375 • Published -
NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models
Paper • 2410.07830 • Published -
A Practical Guide to Fine-tuning Language Models with Limited Data
Paper • 2411.09539 • Published -
Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers
Paper • 2503.00865 • Published • 65 -
A Family of Pretrained Transformer Language Models for Russian
Paper • 2309.10931 • Published • 5 -
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Paper • 2305.12182 • Published • 1 -
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Paper • 2305.07004 • Published • 1 -
CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models
Paper • 2410.18505 • Published • 11 -
SWEb: A Large Web Dataset for the Scandinavian Languages
Paper • 2410.04456 • Published • 1 -
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Paper • 2406.17557 • Published • 98 -
Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
Paper • 2505.17894 • Published • 219 -
ModernGBERT: German-only 1B Encoder Model Trained from Scratch
Paper • 2505.13136 • Published • 21 -
Bielik v3 Small: Technical Report
Paper • 2505.02550 • Published • 68 -
Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance
Paper • 2504.07989 • Published