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 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 …

Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …

While large language models (LLMs) have demonstrated remarkable capabilities across a
range of downstream tasks, a significant concern revolves around their propensity to exhibit …

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 …

Transformers have revolutionized almost all natural language processing (NLP) tasks but
suffer from memory and computational complexity that scales quadratically with sequence …

Motivated by concerns that large-scale diffusion models can produce undesirable output
such as sexually explicit content or copyrighted artistic styles, we study erasure of specific …

Talking about Large Language Models Page 1 key insights ˽ As LLMs become more powerful,
it becomes increasingly tempting to describe LLM-based dialog agents in human-like terms …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

Recent work has shown exciting promise in updating large language models with new
memories, so as to replace obsolete information or add specialized knowledge. However …