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 …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Conversational large language models are fine-tuned for both instruction-following and
safety, resulting in models that obey benign requests but refuse harmful ones. While this …

Language models (LMs) are trained on vast amounts of text data, which may include private
and copyrighted content. Data owners may request the removal of their data from a trained …

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit
harmful unintended behaviors. Finding and fixing these is challenging because the attack …

Large language models are finetuned to refuse questions about hazardous knowledge, but
these protections can often be bypassed. Unlearning methods aim at completely removing …

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively
simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that …

Generative models are rapidly gaining popularity and being integrated into everyday
applications, raising concerns over their safe use as various vulnerabilities are exposed. In …

Language models (LMs) derive their capabilities from extensive training on diverse data,
including potentially copyrighted material. These models can memorize and generate …

Compressing high-capability Large Language Models (LLMs) has emerged as a favored
strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods …