self-rewarding

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data

Class-Conditional self-reward mechanism for improved Text-to-Image models