AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

This paper explores a simple method for improving the zero-shot learning abilities of
language models. We show that instruction tuning--finetuning language models on a …

Transformer architectures are highly expressive because they use self-attention
mechanisms to encode long-range dependencies in the input sequences. In this paper, we …

We evaluate the reasoning abilities of large language models in multilingual settings. We
introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating …

Deep neural-network-based language models (LMs) are increasingly applied to large-scale
protein sequence data to predict protein function. However, being largely black-box models …

India is a multilingual society with 1369 rationalized languages and dialects being spoken
across the country (INDIA, 2011). Of these, the 22 scheduled languages have a staggering …

The scarcity of data presents a critical obstacle to the efficacy of medical vision-language pre-
training (VLP). A potential solution lies in the combination of datasets from various language …

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 …

This paper explores the potential of leveraging Large Language Models (LLMs) for data
augmentation in multilingual commonsense reasoning datasets where the available training …

General-purpose language models have demonstrated impressive capabilities, performing
on par with state-of-the-art approaches on a range of downstream natural language …