List your company

Personalized distractor generation on Discrete_40 Student_1361

40.4AccuracyMCTS-guided reasoning reconstruction framework
7.74416.22224.733.178Aug 15, 2025

Evaluation results

MethodLinks
MCTS-guided reasoning reconstruction frameworkBackbone=Claude-4-Sonnet2025.0840.43.322.76
MCTS-guided reasoning reconstruction frameworkBackbone=Deepseek-V32025.0834.73.242.69
MCTS-guided reasoning reconstruction frameworkBackbone=GPT-4o2025.08313.052.52
MCTS-guided reasoning reconstruction frameworkBackbone=LLaMA-3-70B2025.0828.62.822.33
MCTS-guided reasoning reconstruction frameworkBackbone=GPT-3.5-turbo2025.0828.62.972.38
CoTBackbone=Claude-4-Sonnet2025.0827.82.992.42
MasteryBackbone=Claude-4-Sonnet2025.0826.52.92.31
IOBackbone=Claude-4-Sonnet2025.0826.53.042.47
MasteryBackbone=Deepseek-V32025.0822.92.822.27
IOBackbone=Deepseek-V32025.08222.952.33
CoTBackbone=Deepseek-V32025.0821.22.962.38
MasteryBackbone=GPT-3.5-turbo2025.0818.82.62.07
IOBackbone=LLaMA-3-70B2025.0818.42.542.11
Level+SimilarityBackbone=Claude-4-Sonnet2025.0818.42.792.34
IOBackbone=GPT-3.5-turbo2025.08182.62.1
CoTBackbone=GPT-3.5-turbo2025.08182.642.16
CoTBackbone=GPT-4o2025.08182.722.26
MasteryBackbone=LLaMA-3-70B2025.0817.12.552.05
MasteryBackbone=GPT-4o2025.0817.12.762.31
CoTBackbone=LLaMA-3-70B2025.0816.72.592.15
SimilarityBackbone=Deepseek-V32025.0816.72.622.12
IOBackbone=GPT-4o2025.0816.32.692.26
Level+RandomBackbone=Deepseek-V32025.0815.52.582.18
RandomBackbone=GPT-3.5-turbo2025.0815.52.452.04
Level+RandomBackbone=GPT-3.5-turbo2025.0815.52.361.98
LevelBackbone=GPT-4o2025.0815.52.482.09
Level+RandomBackbone=LLaMA-3-70B2025.0815.12.351.96
SimilarityBackbone=Claude-4-Sonnet2025.0815.12.912.39
SimilarityBackbone=GPT-3.5-turbo2025.0815.12.542.07
Level+RandomBackbone=GPT-4o2025.0815.12.512.16
LevelBackbone=LLaMA-3-70B2025.0814.72.341.93
LevelBackbone=Claude-4-Sonnet2025.0814.72.752.38
Level+RandomBackbone=Claude-4-Sonnet2025.0814.72.672.25
RandomBackbone=GPT-4o2025.0814.32.492.08
LevelBackbone=GPT-3.5-turbo2025.0813.92.361.9
Level+SimilarityBackbone=GPT-3.5-turbo2025.0813.92.291.89
Level+SimilarityBackbone=GPT-4o2025.0813.92.442.11
RandomBackbone=Deepseek-V32025.0813.52.542.07
RandomBackbone=Claude-4-Sonnet2025.0813.52.912.48
Level+SimilarityBackbone=LLaMA-3-70B2025.0813.12.31.88
SimilarityBackbone=GPT-4o2025.0812.72.632.24
SimilarityBackbone=LLaMA-3-70B2025.0811.42.31.92
LevelBackbone=Deepseek-V32025.08112.492.08
Level+SimilarityBackbone=Deepseek-V32025.0810.62.441.99
RandomBackbone=LLaMA-3-70B2025.0892.171.78