SimPO: Simple Preference Optimization with a Reference-Free Reward.
Yu MengMengzhou XiaDanqi ChenPublished in: CoRR (2024)
Keyphrases
- information retrieval
- search algorithm
- optimization algorithm
- optimization strategies
- data mining
- highly reliable
- case study
- optimization model
- user preferences
- artificial neural networks
- constrained optimization
- optimization methods
- global optimization
- databases
- support vector
- multi agent
- machine learning
- real world