Bradley-Terry

Researchers propose RENEW, a method that uses human preferences over imagined rollouts to repair model exploitation in offline reinforcement learning world models, achieving practical sample efficienc…

A developer trained a large language model from scratch using plain PyTorch, implementing the full post-training pipeline including SFT, reward modeling, DPO, PPO, and GRPO on public datasets, all run…

Researchers propose structural uncertainty, a framework that measures consistency in LLM logical reasoning by analyzing self-preference-induced rankings over sampled solutions. Across five LLMs and ei…