相关论文: Adapting BigScience Multilingual Model to Unseen L…

Recent models such as XLS-R and Whisper have made multilingual speech technologies more accessible by pre-training on audio from around 100 spoken languages each. However, there are thousands of spoken languages worldwide, and adapting to…

In this study, we introduce Orion-14B, a collection of multilingual large language models with 14 billion parameters. We utilize a data scheduling approach to train a foundational model on a diverse corpus of 2.5 trillion tokens, sourced…

Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving…

Providing better language tools for low-resource and endangered languages is imperative for equitable growth. Recent progress with massively multilingual pretrained models has proven surprisingly effective at performing zero-shot transfer…

The impressive development of large language models (LLMs) is expanding into the realm of large multimodal models (LMMs), which incorporate multiple types of data beyond text. However, the nature of multimodal models leads to significant…

Large language models (LLMs) use pretraining to predict the subsequent word; however, their expansion requires significant computing resources. Numerous big tech companies and research institutes have developed multilingual LLMs (MLLMs) to…

Instruction tuning a large language model with multiple languages can prepare it for multilingual downstream tasks. Nonetheless, it is yet to be determined whether having a handful of languages is sufficient, or whether the benefits…

Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively…

As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings. The BigScience workshop, a 1-year international and multidisciplinary initiative,…

Large language models are powerful but often limited by high computational cost, privacy concerns, and English-centric training. Recent progress demonstrates that small, efficient models with around one billion parameters can deliver strong…

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a…

Results reported in large-scale multilingual evaluations are often fragmented and confounded by factors such as target languages, differences in experimental setups, and model choices. We propose a framework that disentangles these…

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen…

The development of open-source, multilingual medical language models can benefit a wide, linguistically diverse audience from different regions. To promote this domain, we present contributions from the following: First, we construct a…

The pretraining of state-of-the-art large language models now requires trillions of words of text, which is orders of magnitude more than available for the vast majority of languages. While including text in more than one language is an…

Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide…