Paraphrase Classification
75AccuracyPara-PLUIE
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Para-PLUIEbackbone=Phi, Threshold=02026.02 | 75 | 49 | 66 | 56 | |
| *-PLUIEbackbone=Phi, Threshold=02026.02 | 74 | 54 | 61 | 58 | |
| LLM-Yes/Nobackbone=Phi2026.02 | 74 | 50 | 64 | 56 | |
| Para-PLUIEbackbone=Phi, Threshold=-7.472026.02 | 73 | 73 | 57 | 64 | |
| Para-PLUIEbackbone=Llama, Threshold=02026.02 | 72 | 48 | 58 | 53 | |
| *-PLUIEbackbone=Phi, Threshold=-7.632026.02 | 71 | 77 | 54 | 63 | |
| LLM-Yes/Nobackbone=Llama2026.02 | 71 | 48 | 56 | 52 | |
| *-PLUIEbackbone=Llama, Threshold=02026.02 | 70 | 64 | 53 | 58 | |
| Para-PLUIEbackbone=Llama, Threshold=-11.912026.02 | 70 | 66 | 54 | 59 | |
| *-PLUIEbackbone=Llama, Threshold=-4.072026.02 | 67 | 71 | 50 | 59 | |
| Random weighted2026.02 | 56 | 32 | 32 | 32 | |
| Random uniform2026.02 | 50 | 50 | 32 | 40 | |
| Modern BertScoreThreshold=0.842026.02 | 33 | 100 | 33 | 49 | |
| BERTScoreThreshold=0.802026.02 | 33 | 100 | 33 | 49 | |
| METEORThreshold=0.432026.02 | 33 | 100 | 33 | 49 | |
| BLEUThreshold=0.002026.02 | 33 | 100 | 33 | 49 | |
| LevenshteinThreshold=0.712026.02 | 33 | 100 | 33 | 49 |