Paper summary
Paper summary: Towards a Unified View of Preference Learning for Large Language Models: A Survey
A survey that breaks every LLM preference-alignment method into four components, model, data, feedback and algorithm, to show how RLHF, DPO and their relatives connect.
- Model, data, feedback, algorithm: four components that every preference-learning method combines differently.
- Seeing methods as combinations makes it easier to spot unexplored ones.