AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

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 …

Pre-trained language models can be surprisingly adept at tasks they were not explicitly
trained on, but how they implement these capabilities is poorly understood. In this paper, we …

The capabilities of large language models (LLMs) have sparked debate over whether such
systems just learn an enormous collection of superficial statistics or a set of more coherent …

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 …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Despite rapid adoption and deployment of large language models (LLMs), the internal
computations of these models remain opaque and poorly understood. In this work, we seek …

End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to
understand. This has given rise to numerous efforts towards model explainability in recent …

A growing body of work makes use of probing in order to investigate the working of neural
models, often considered black boxes. Recently, an ongoing debate emerged surrounding …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …