Recently, ChatGPT, along with DALL-E-2 and Codex, has been gaining significant attention
from society. As a result, many individuals have become interested in related resources and …

Large Language Models (LLMs) have recently demonstrated remarkable capabilities in
natural language processing tasks and beyond. This success of LLMs has led to a large …

Finetuning language models on a collection of datasets phrased as instructions has been
shown to improve model performance and generalization to unseen tasks. In this paper we …

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large
language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine …

We report the development of GPT-4, a large-scale, multimodal model which can accept
image and text inputs and produce text outputs. While less capable than humans in many …

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 …

We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and
reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is …

We study the design decision of publicly available instruction tuning methods, by
reproducing and breaking down the development of Flan 2022 (Chung et al., 2022) …

Large language models trained for safety and harmlessness remain susceptible to
adversarial misuse, as evidenced by the prevalence of “jailbreak” attacks on early releases …

Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …