論文紹介：Direct Preference Optimization: Your Language Model is Secretly a Reward Model

DeepLearning.AI on Instagram: "Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll at the link in bio or comment "LLM" to receive the link in your inbox."

DPT: Dynamic Preference Transfer for Cross-Domain Sequential Recommendation | Proceedings of the 34th ACM International Conference on Information and Knowledge Management