Distractor Generation on MCQ
30.5P@1GPT-3(few-shot-COT-k-NN)
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GPT-3(few-shot-COT-k-NN)Approach=Prompting2026.04 | 30.5 | 10.17 | 19.43 | 36.29 | 40.6 | 0 | 0 | |
| GPT-3(few-shot-k-NN)Approach=Prompting2026.04 | 29.73 | 9.91 | 19.69 | 36.62 | 42.37 | 0 | 0 | |
| GPT-3(few-shot-COT-random)Approach=Prompting2026.04 | 28.96 | 9.65 | 19.05 | 36.04 | 42.08 | 0 | 0 | |
| GPT-3(zero-shot)Approach=Prompting2026.04 | 25.87 | 8.62 | 17.63 | 32.56 | 38.33 | 0 | 0 | |
| GPT-3(few-shot-random)Approach=Prompting2026.04 | 25.87 | 8.62 | 18.28 | 33.72 | 40.68 | 0 | 0 | |
| T5(contrast)Approach=Text2Text2026.04 | 22.78 | 7.59 | 15.7 | 28.57 | 32.33 | 14.67 | 10.81 | |
| TinyLlamaApproach=Instruction Tuning2026.04 | 22.78 | 7.59 | 15.06 | 28.44 | 33.16 | 3.09 | 1.54 | |
| T5-CSG-DS(beam)Approach=CSG-DS2026.04 | 17.37 | 5.79 | 13.38 | 24.2 | 30.11 | 36.29 | 0.39 | |
| T5(multi-task)Approach=Text2Text2026.04 | 15.06 | 5.02 | 12.23 | 19.95 | 23.54 | 19.31 | 15.83 | |
| GPT-3-CSG-DS(clustering)Approach=CSG-DS2026.04 | 14.29 | 4.76 | 8.49 | 18.92 | 22.95 | 0.39 | 0 | |
| T5(base)Approach=Text2Text2026.04 | 14.29 | 4.76 | 10.81 | 20.14 | 24.68 | 17.76 | 18.15 | |
| T5-CSG-DS(clustering)Approach=CSG-DS2026.04 | 11.58 | 3.86 | 7.72 | 16.47 | 20.96 | 18.15 | 0 |