Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Large Language Models (LLMs) went from non-existent to ubiquitous in the machine
learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify …

Abstract We introduce Inference-Time Intervention (ITI), a technique designed to enhance
the" truthfulness" of large language models (LLMs). ITI operates by shifting model activations …

Large language models (LLMs) pretrained on vast source code have achieved prominent
progress in code intelligence. However, existing code LLMs have two main limitations in …

Responsible innovation on large-scale Language Models (LMs) requires foresight into and
in-depth understanding of the risks these models may pose. This paper develops a …

Controlling the behavior of language models (LMs) without re-training is a major open
problem in natural language generation. While recent works have demonstrated successes …

Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …

Making language models bigger does not inherently make them better at following a user's
intent. For example, large language models can generate outputs that are untruthful, toxic, or …

A longstanding goal of the field of AI is a method for learning a highly capable, generalist
agent from diverse experience. In the subfields of vision and language, this was largely …

Toxic language detection systems often falsely flag text that contains minority group
mentions as toxic, as those groups are often the targets of online hate. Such over-reliance …