Reinforcement Learning

Training language models to follow instructions with human feedback

<h2 class="text-2xl font-bold mb-4">Summary</h2> This paper from OpenAI introduces InstructGPT, a language model trained to follow instructions. The core innovation lies in leveraging human feedback ...

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

<h2 class="text-2xl font-bold mb-4">Summary</h2> This paper introduces Direct Preference Optimization (DPO), a novel approach for aligning language models with human preferences. DPO offers a simplif...

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

<h2 class="text-2xl font-bold mb-4">Summary</h2> The DeepSeek-R1 paper introduces a novel approach to enhance reasoning capabilities in Large Language Models (LLMs) using Reinforcement Learning (RL)....