Probing classifiers have emerged as one of the prominent methodologies for interpreting
and analyzing deep neural network models of natural language processing. The basic idea …

Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …

Large language models (LLMs) have been shown to be able to perform new tasks based on
a few demonstrations or natural language instructions. While these capabilities have led to …

Language models show a surprising range of capabilities, but the source of their apparent
competence is unclear. Do these networks just memorize a collection of surface statistics, or …

We analyze the storage and recall of factual associations in autoregressive transformer
language models, finding evidence that these associations correspond to localized, directly …

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 …

Convolutional neural networks (CNNs) have so far been the de-facto model for visual data.
Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or …

External audits of AI systems are increasingly recognized as a key mechanism for AI
governance. The effectiveness of an audit, however, depends on the degree of access …

While large pre-trained models have enabled impressive results on a variety of downstream
tasks, the largest existing models still make errors, and even accurate predictions may …

Interpretable machine learning has exploded as an area of interest over the last decade,
sparked by the rise of increasingly large datasets and deep neural networks …