This repository contains the summaries of papers related to the alignment problem in Natural Language Processing (NLP), and discussions with Kyoungwhan Mheen.
All the summaries and discussions are either in Korean (한국어) or English.
This covers several papers related to the alignment problem and the methods such as instruction tuning and Reinforcement Learning from Human Feedback (RLHF) that attempt to solve it.
You can click the document emoji (📄) to read the summary if available.