Personalized distractor generation on Discrete_40 Student_1361

40.4Accuracy

MCTS-guided reasoning reconstruction framework

Updated 1mo ago

Evaluation Results

Method
MCTS-guided reasoning reconstruction framework 2025.08	40.4	3.32	2.76
MCTS-guided reasoning reconstruction framework 2025.08	34.7	3.24	2.69
MCTS-guided reasoning reconstruction framework 2025.08	31	3.05	2.52
MCTS-guided reasoning reconstruction framework 2025.08	28.6	2.82	2.33
MCTS-guided reasoning reconstruction framework 2025.08	28.6	2.97	2.38
CoT 2025.08	27.8	2.99	2.42
Mastery 2025.08	26.5	2.9	2.31
IO 2025.08	26.5	3.04	2.47
Mastery 2025.08	22.9	2.82	2.27
IO 2025.08	22	2.95	2.33
CoT 2025.08	21.2	2.96	2.38
Mastery 2025.08	18.8	2.6	2.07
IO 2025.08	18.4	2.54	2.11
Level+Similarity 2025.08	18.4	2.79	2.34
IO 2025.08	18	2.6	2.1
CoT 2025.08	18	2.64	2.16
CoT 2025.08	18	2.72	2.26
Mastery 2025.08	17.1	2.55	2.05
Mastery 2025.08	17.1	2.76	2.31
CoT 2025.08	16.7	2.59	2.15
Similarity 2025.08	16.7	2.62	2.12
IO 2025.08	16.3	2.69	2.26
Level+Random 2025.08	15.5	2.58	2.18
Random 2025.08	15.5	2.45	2.04
Level+Random 2025.08	15.5	2.36	1.98
Level 2025.08	15.5	2.48	2.09
Level+Random 2025.08	15.1	2.35	1.96
Similarity 2025.08	15.1	2.91	2.39
Similarity 2025.08	15.1	2.54	2.07
Level+Random 2025.08	15.1	2.51	2.16
Level 2025.08	14.7	2.34	1.93
Level 2025.08	14.7	2.75	2.38
Level+Random 2025.08	14.7	2.67	2.25
Random 2025.08	14.3	2.49	2.08
Level 2025.08	13.9	2.36	1.9
Level+Similarity 2025.08	13.9	2.29	1.89
Level+Similarity 2025.08	13.9	2.44	2.11
Random 2025.08	13.5	2.54	2.07
Random 2025.08	13.5	2.91	2.48
Level+Similarity 2025.08	13.1	2.3	1.88
Similarity 2025.08	12.7	2.63	2.24
Similarity 2025.08	11.4	2.3	1.92
Level 2025.08	11	2.49	2.08
Level+Similarity 2025.08	10.6	2.44	1.99
Random 2025.08	9	2.17	1.78