Large language models (LLMs) have come closest among all models to date to mastering
human language, yet opinions about their linguistic and cognitive capabilities remain split …

Large, pre-trained language models (PLMs) such as BERT and GPT have drastically
changed the Natural Language Processing (NLP) field. For numerous NLP tasks …

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 …

Modern machine learning has subverted and bypassed the theoretical framework of
Chomsky's generative approach to linguistics, including its core claims to particular insights …

Large language models (LLMs) have demonstrated impressive capabilities in natural
language processing. However, their internal mechanisms are still unclear and this lack of …

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 …

How to efficiently serve ever-larger trained natural language models in practice has become
exceptionally challenging even for powerful cloud servers due to their prohibitive …

Large pretrained (eg," foundation") models exhibit distinct capabilities depending on the
domain of data they are trained on. While these domains are generic, they may only barely …

Abstract Concept erasure aims to remove specified features from a representation. It can
improve fairness (eg preventing a classifier from using gender or race) and interpretability …

Text-to-image generative models are a new and powerful way to generate visual artwork.
However, the open-ended nature of text as interaction is double-edged; while users can …