Modern artificial intelligence (AI) systems are powered by foundation models. This paper
presents a new set of foundation models, called Llama 3. It is a herd of language models …

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

Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they
still struggle with scenarios that involves complex reasoning and planning. Self-correction …

A central piece in enabling intelligent agentic behavior in foundation models is to make them
capable of introspecting upon their behavior, reasoning, and correcting their mistakes as …

Common self-improvement approaches for large language models (LLMs), such as STaR,
iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving …

The math abilities of large language models can represent their abstract reasoning ability. In
this paper, we introduce and open-source our math reasoning LLMs InternLM-Math which is …

The recent development of chain-of-thought (CoT) decoding has enabled large language
models (LLMs) to generate explicit logical reasoning paths for complex problem-solving …

Current AI alignment methodologies rely on human-provided demonstrations or judgments,
and the learned capabilities of AI systems would be upper-bounded by human capabilities …

Mathematical reasoning presents a significant challenge for Large Language Models
(LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring …

A fundamental skill among human developers is the ability to understand and reason about
program execution. As an example, a programmer can mentally simulate code execution in …