Binary Classification on Interaction Dataset (DI)
98AccuracyCARO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CAROCategory=12026.02 | 98 | 0.92 | |
| CAROCategory=72026.02 | 97 | 0.54 | |
| GradeOptCategory=12026.02 | 96 | 0.84 | |
| CAROCategory=52026.02 | 96 | 0.78 | |
| CAROCategory=32026.02 | 95 | 0.89 | |
| GradeOptCategory=52026.02 | 95 | 0.72 | |
| GradeOptCategory=72026.02 | 95 | 0.48 | |
| NaiveCategory=12026.02 | 94 | 0.79 | |
| CAROCategory=112026.02 | 94 | 0.64 | |
| CAROCategory=22026.02 | 93 | 0.87 | |
| CAROCategory=92026.02 | 90 | -0.02 | |
| GradeOptCategory=112026.02 | 90 | 0.5 | |
| CAROCategory=Avg2026.02 | 90 | 0.55 | |
| CAROPrompting Strategy=Confusion-Aware Rubric Optimization2026.02 | 90 | 0.55 | |
| GradeOptCategory=22026.02 | 88 | 0.76 | |
| CAROCategory=62026.02 | 87 | 0.21 | |
| NaiveCategory=22026.02 | 86 | 0.71 | |
| GradeOptCategory=32026.02 | 85 | 0.61 | |
| NaiveCategory=32026.02 | 82 | 0.52 | |
| CAROCategory=102026.02 | 82 | 0.47 | |
| CAROCategory=42026.02 | 81 | 0.62 | |
| NaiveCategory=72026.02 | 77 | 0.11 | |
| GradeOptCategory=Avg2026.02 | 75 | 0.43 | |
| GradeOptPrompting Strategy=GradeOpt aggregate feedback2026.02 | 75 | 0.43 | |
| CAROCategory=82026.02 | 74 | 0.12 | |
| GradeOptCategory=62026.02 | 73 | 0.09 | |
| GradeOptCategory=102026.02 | 72 | 0.41 | |
| GradeOptCategory=42026.02 | 64 | 0.36 | |
| NaiveCategory=52026.02 | 62 | 0.18 | |
| NaiveCategory=112026.02 | 60 | 0.14 | |
| NaiveCategory=Avg2026.02 | 58 | 0.25 | |
| NaivePrompting Strategy=Naive prompting2026.02 | 58 | 0.25 | |
| NaiveCategory=42026.02 | 52 | 0.19 | |
| GradeOptCategory=82026.02 | 44 | 0.04 | |
| NaiveCategory=62026.02 | 42 | 0.03 | |
| NaiveCategory=102026.02 | 42 | 0.14 | |
| GradeOptCategory=92026.02 | 27 | 0.01 | |
| NaiveCategory=82026.02 | 22 | 0.03 | |
| NaiveCategory=92026.02 | 15 | -0.04 |