Glossary

Use supervised fine-tuning to save time and money when realigning language models to user preferences. Get an overview of SFT and its role.

Discover how Reasoning with Reinforced Fine-Tuning (ReFT) improves generalizability in learning LLMs for math problem-solving. Find out more here.

Self-Rewarding Language Models (SRLMs) utilize an LLM’s own judgment to provide feedback...

SELF-ALIGN, a novel approach that combines principle-driven reasoning and the generative power of LLMs, can self-align AI agents with minimal human supervision.

RLAIF, a reinforcement learning technique that utilizes AI feedback to instruct large language models (LLMs), offers a scalable and cost-effective alternative to RLHF.