List your company

Distractor Generation on Discrete_40

3.25PlausibilityMCTS-guided reasoning reconstruction framework
2.51162.70332.8953.0867Aug 15, 2025

Evaluation results

MethodLinks
MCTS-guided reasoning reconstruction frameworkBackbone Model=Claude-4-Sonnet2025.083.252.64
MCTS-guided reasoning reconstruction frameworkBackbone Model=Deepseek-V32025.083.162.59
CoTBackbone Model=Deepseek-V32025.082.892.27
MCTS-guided reasoning reconstruction frameworkBackbone Model=GPT-4o2025.082.882.43
CoTBackbone Model=Claude-4-Sonnet2025.082.852.39
MCTS-guided reasoning reconstruction frameworkBackbone Model=GPT-3.5-turbo2025.082.812.23
MCTS-guided reasoning reconstruction frameworkBackbone Model=LLaMA-3-70B2025.082.772.32
CoTBackbone Model=GPT-4o2025.082.722.25
CoTBackbone Model=GPT-3.5-turbo2025.082.642.12
CoTBackbone Model=LLaMA-3-70B2025.082.542.13