12 accepted papers
Language models (LMs) can be directed to perform user- and context-dependent tasks by using labeled examples or natural language prompts. But selecting examples or writing prompts can be challenging---especially in tasks that require users to precisely articulate nebulous preferences or reason about…
Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden states that are sparse, discrete, and more interpretable by quantizing their continuous features into what we call codeb…
We investigate a family of simple long-context attacks on large language models: prompting with hundreds of demonstrations of undesirable behavior. This attack is newly feasible with the larger context windows recently deployed by language model providers like Google DeepMind, OpenAI and Anthropic.…
What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations can be useful in the foundation model setting, where the go…
When we transfer a pretrained language model to a new language, there are many axes of variation that change at once. To disentangle the impact of different factors like syntactic similarity and vocabulary similarity, we propose a set of \emph{controlled transfer studies}: we systematically transfor…
Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, real world tasks are often poorly specified, and agents must deduce the intended behavior from a combination of context, instructions, and examples. We investigate how both humans and models beh…
Analysis of compressible turbulent flows is essential for applications related to propulsion, energy generation, and the environment. Here, we present BLASTNet 2.0, a 2.2 TB network-of-datasets containing 744 full-domain samples from 34 high-fidelity direct numerical simulations, which addresses th…
Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object classifier trained on red squares and blue circles: when encountering blue squares, the intended behavior is undefined. We in…
Universal self-supervised (SSL) algorithms hold enormous promise for making machine learning accessible to high-impact domains such as protein biology, manufacturing, and genomics. We present DABS 2.0: a set of improved datasets and algorithms for advancing research on universal SSL. We extend the r…
Self-supervised learning algorithms, including BERT and SimCLR, have enabled significant strides in fields like natural language processing, computer vision, and speech processing. However, these algorithms are domain-specific, meaning that new self-supervised learning algorithms must be developed f…
Many recent methods for unsupervised representation learning train models to be invariant to different "views," or distorted versions of an input. However, designing these views requires considerable trial and error by human experts, hindering widespread adoption of unsupervised representation learn…
Language exhibits structure at a wide range of scales, from subwords to words, sentences, paragraphs, and documents. We propose building models that isolate scale-specific information in deep representations, and develop methods for encouraging models during training to learn more about particular s…