Code Consistency Preference Optimization Verification for Language Model Alignment
TL;DR
This work proposes a method that generates computationally sound solutions with dependency graphs for execution-consistent preference optimization, and achieves 50.1% accuracy on PhyX multimodal physics reasoning, surpassing DeepSeek-R1 and OpenAI o3-mini.
Abstract
Execution-based verification enhances large language models'mathematical reasoning through computational soundness and dependency-aware filtering. However, prior preference optimization methods relying on Bradley-Terry reward models fail to capture the logical dependencies and execution consistency needed for scientific tasks. We propose a method that generates computationally sound solutions with dependency graphs for execution-consistent preference optimization. We first build a scientific reasoning dataset using UltraFeedback prompts, model generations, verification, and consistency results. Then we extract reasoning step expressions, prerequisites, and derivability relationships to construct dependency graphs and compute execution consistency scores. These scores are appended to each step, creating paired training data. Fine-tuning Llama-3-8B and DeepSeekMath-7B yields significant gains: +17.0% on MATH and +15.1% on GSM8K. Extending our Scientific Feasibility Control framework achieves 50.1% accuracy on PhyX multimodal physics reasoning, surpassing DeepSeek-R1 (49.8%) and OpenAI o3-mini (48.2%), with 91.7% scientific validity coverage at alpha=0.10 and 73% fewer scientific law violations, resulting in the CCPO model family.
