Step-level Value Preference Optimization for Mathematical Reasoning.
Guoxin ChenMinpeng LiaoChengxi LiKai FanPublished in: CoRR (2024)
Keyphrases
- global optimization
- post processing
- optimization algorithm
- discrete optimization
- human reasoning
- higher level
- optimization methods
- multi attribute
- optimization process
- levels of abstraction
- mathematical proofs
- machine learning
- cp nets
- consistency checking
- reasoning systems
- optimization problems
- fuzzy logic
- knowledge representation