List your company

Personalized Distractor Generation on Eedi 100 Student 1361

32.1AccuracyMCTS-guided reasoning reconstruction framework
9.32415.23721.1527.063Aug 15, 2025

Evaluation results

MethodLinks
MCTS-guided reasoning reconstruction frameworkBackbone=Deepseek-V32025.0832.13.562.98
MCTS-guided reasoning reconstruction frameworkBackbone=GPT-4o2025.0828.23.172.64
CoTBackbone=Deepseek-V32025.0827.13.352.83
MCTS-guided reasoning reconstruction frameworkBackbone=Claude-4-Sonnet2025.08273.723.31
IOBackbone=Deepseek-V32025.0826.43.292.83
RandomBackbone=Deepseek-V32025.0825.83.12.63
MasteryBackbone=Deepseek-V32025.0825.53.192.7
LevelBackbone=GPT-4o2025.0825.42.672.39
MasteryBackbone=GPT-4o2025.0825.43.062.61
CoTBackbone=Claude-4-Sonnet2025.0825.33.523.12
LevelBackbone=Deepseek-V32025.0825.12.82.5
Level+RandomBackbone=Deepseek-V32025.0824.82.752.44
Level+SimilarityBackbone=Deepseek-V32025.0824.72.752.44
Level+RandomBackbone=GPT-4o2025.0824.72.652.34
IOBackbone=GPT-4o2025.0824.432.53
SimilarityBackbone=Deepseek-V32025.0824.23.152.71
IOBackbone=Claude-4-Sonnet2025.0824.13.513.1
Level+RandomBackbone=Claude-4-Sonnet2025.08242.882.63
Level+SimilarityBackbone=GPT-4o2025.0823.92.632.33
Level+SimilarityBackbone=Claude-4-Sonnet2025.0823.72.832.56
CoTBackbone=GPT-4o2025.0823.732.54
MasteryBackbone=Claude-4-Sonnet2025.0823.53.342.82
LevelBackbone=Claude-4-Sonnet2025.08232.922.66
SimilarityBackbone=GPT-4o2025.0822.92.952.55
SimilarityBackbone=Claude-4-Sonnet2025.0822.83.443.09
RandomBackbone=Claude-4-Sonnet2025.0822.33.362.96
MCTS-guided reasoning reconstruction frameworkBackbone=GPT-3.5-turbo2025.0822.13.122.53
RandomBackbone=GPT-4o2025.0818.42.712.32
MCTS-guided reasoning reconstruction frameworkBackbone=LLaMA-3-70B2025.0817.72.932.45
IOBackbone=GPT-3.5-turbo2025.0817.42.732.25
LevelBackbone=GPT-3.5-turbo2025.0816.62.392.11
CoTBackbone=LLaMA-3-70B2025.0816.22.742.27
LevelBackbone=LLaMA-3-70B2025.0815.72.52.22
MasteryBackbone=GPT-3.5-turbo2025.0815.52.742.28
CoTBackbone=GPT-3.5-turbo2025.0814.92.732.25
IOBackbone=LLaMA-3-70B2025.0814.22.742.3
MasteryBackbone=LLaMA-3-70B2025.08142.682.21
Level+RandomBackbone=LLaMA-3-70B2025.0813.72.432.17
Level+SimilarityBackbone=LLaMA-3-70B2025.0813.72.432.19
Level+SimilarityBackbone=GPT-3.5-turbo2025.0813.12.161.88
Level+RandomBackbone=GPT-3.5-turbo2025.0812.92.161.9
SimilarityBackbone=LLaMA-3-70B2025.0812.72.82.43
SimilarityBackbone=GPT-3.5-turbo2025.0812.22.622.22
RandomBackbone=GPT-3.5-turbo2025.08112.562.13
RandomBackbone=LLaMA-3-70B2025.0810.22.662.31