AlignGPT
Public“This project implements a mini LLM alignment pipeline using Reinforcement Learning from Human Feedback (RLHF). It includes training a reward model from human-annotated preference data, fine-tuning the language model via policy optimization, and performing ablation studies to evaluate robustness, fairness, and alignment trade-offs.”
ai-safetyalignmentdeep-learningdpofine-tuninghuman-feedbacklanguage-modelsmachine-learningnlppolicy-optimization
Creat：2025-10-04T00:47:59
Update：2025-10-06T02:49:12
1
Stars
0
Stars Increase