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 …

Large language models (LLMs) are rapidly being adopted in healthcare, necessitating
standardized reporting guidelines. We present transparent reporting of a multivariable …

Mathematical reasoning poses a significant challenge for language models due to its
complex and structured nature. In this paper, we introduce DeepSeekMath 7B, which …

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 …

In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a
pivotal methodology for transferring advanced capabilities from leading proprietary LLMs …

This paper studies the alignment process of generative models with Reinforcement Learning
from Human Feedback (RLHF). We first identify the primary challenges of existing popular …

Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as
efficient alternatives to reinforcement learning from human feedback (RLHF), that do not …

We present the workflow of Online Iterative Reinforcement Learning from Human Feedback
(RLHF) in this technical report, which is widely reported to outperform its offline counterpart …

We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base,
Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward. Our models are open access …

Common methods for aligning large language models (LLMs) with desired behaviour
heavily rely on human-labelled data. However, as models grow increasingly sophisticated …