This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness.

InstructGPT implements RLHF through several stages, including Supervised Fine-Tuning (SFT), reward model training, and Proximal Policy Optimization (PPO).

Preferences serve as an alternative but recent work rarely considers preference learning given multiple tasks.

Then it fine-tunes the LLM to maximize the learned reward using RL techniques.

With the advent of large language models (LLMs), reinforcement learning from human feedback (RLHF) has emerged as a pivotal technological paradigm to align models' behaviors with human values [

Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from human brings safety and AI alignment to the learning process.