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 …

AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable
capabilities across image, audio, video, and text understanding. The Gemini family consists …

How do large language models (LLMs) develop and evolve over the course of training?
How do these patterns change as models scale? To answer these questions, we introduce …

In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights …

Large Language Models (LLMs) have made substantial progress in the past several months,
shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' …

The BigCode project, an open-scientific collaboration focused on the responsible
development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In …

Language models (LMs) are pretrained on diverse data sources, including news, discussion
forums, books, and online encyclopedias. A significant portion of this data includes opinions …

Text-to-image models suffer from various safety issues that may limit their suitability for
deployment. Previous methods have separately addressed individual issues of bias …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …