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 …

AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Large multimodal models (LMM) have recently shown encouraging progress with visual
instruction tuning. In this paper we present the first systematic study to investigate the design …

Because" out-of-the-box" large language models are capable of generating a great deal of
objectionable content, recent work has focused on aligning these models in an attempt to …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

Optimizing large language models (LLMs) for downstream use cases often involves the
customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama …

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

This paper studies extractable memorization: training data that an adversary can efficiently
extract by querying a machine learning model without prior knowledge of the training …

The rapid progress in open-source large language models (LLMs) is significantly advancing
AI development. Extensive efforts have been made before model release to align their …

Every major technical invention resurfaces the dual-use dilemma—the new technology has
the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such …