Vision-language models trained with contrastive learning on large-scale noisy data are
becoming increasingly popular for zero-shot recognition problems. In this paper we improve the …

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large
language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-…

Large language models, which are often trained for hundreds of thousands of compute days,
have shown remarkable capabilities for zero- and few-shot learning. Given their …

Large-scale generative language models such as GPT-3 are competitive few-shot learners.
While these models are known to be able to jointly represent many different languages, their …

We present a new kind of question answering dataset, OpenBookQA, modeled after open
book exams for assessing human understanding of a subject. The open book that comes with …

The emergence of user forums in electronic news media has given rise to the proliferation of
opinion manipulation trolls. Finding such trolls automatically is a hard task, as there is no …

We introduce a neural reading comprehension model that integrates external commonsense
knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only …

Recent work has shown that fine-tuning large pre-trained language models on a collection
of tasks described via instructions, aka instruction-tuning, improves their zero and few-shot …

Mixture of Experts layers (MoEs) enable efficient scaling of language models through
conditional computation. This paper presents a detailed empirical study of how autoregressive …

There are different definitions of what a troll is. Certainly, a troll can be somebody who teases
people to make them angry, or somebody who offends people, or somebody who wants to …