Recommendation on REDIAL (test)
50Recall@10Llama2 + FNSCRS
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Llama2 + FNSCRSEvaluation Protocol=User Simulator2025.07 | 50 | 71.42 | — | — | — | — | 28.65 | |
| Llama2 + SDEvaluation Protocol=User Simulator2025.07 | 45.71 | 65.46 | — | — | — | — | 24.2 | |
| Llama2 + CRCRSEvaluation Protocol=User Simulator2025.07 | 45.19 | 63.08 | — | — | — | — | 27.95 | |
| BARCOR + FNSCRSEvaluation Protocol=User Simulator2025.07 | 44.69 | 63.35 | — | — | — | — | 27.77 | |
| UniCRS + FNSCRSEvaluation Protocol=User Simulator2025.07 | 43.65 | 63.42 | — | — | — | — | 24.44 | |
| Llama2Evaluation Protocol=User Simulator2025.07 | 42.83 | 61.89 | — | — | — | — | 24.33 | |
| UniCRS + CRCRSEvaluation Protocol=User Simulator2025.07 | 41.5 | 59.96 | — | — | — | — | 25.02 | |
| UniCRS + SDEvaluation Protocol=User Simulator2025.07 | 39.12 | 59.78 | — | — | — | — | 22.07 | |
| BARCOR + SDEvaluation Protocol=User Simulator2025.07 | 36.74 | 54.71 | — | — | — | — | 21.95 | |
| UniCRSEvaluation Protocol=User Simulator2025.07 | 36.44 | 55.72 | — | — | — | — | 20.46 | |
| BARCOR + CFCRSEvaluation Protocol=User Simulator2025.07 | 34.17 | 51.23 | — | — | — | — | 19.87 | |
| BARCOREvaluation Protocol=User Simulator2025.07 | 23.68 | 43.03 | — | — | — | — | 11.34 | |
| C2-CRS2022.01 | 23.3 | 40.7 | — | — | — | — | 5.3 | |
| HyFairCRS2025.07 | 22.37 | 43.82 | 7.98 | 8.99 | 12.97 | 15.9 | — | |
| Llama2 + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 22.37 | 44.2 | — | — | — | — | 4.46 | |
| RevCore2022.01 | 22 | 39.6 | — | — | — | — | 4.6 | |
| HiCore2025.07 | 21.92 | 41.63 | 7.75 | 8.74 | 11.07 | 15.58 | — | |
| Llama2 + SDEvaluation Protocol=Offline Dataset2025.07 | 21.77 | 43.58 | — | — | — | — | 3.97 | |
| Llama2 + CRCRSEvaluation Protocol=Offline Dataset2025.07 | 21.57 | 42.24 | — | — | — | — | 4.27 | |
| BARCOR + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 21.26 | 43.84 | — | — | — | — | 4.31 | |
| UniCRS + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 20.93 | 42.74 | — | — | — | — | 3.76 | |
| Llama2Evaluation Protocol=Offline Dataset2025.07 | 20.74 | 41.34 | — | — | — | — | 3.93 | |
| UniCRS + SDEvaluation Protocol=Offline Dataset2025.07 | 20.27 | 42.26 | — | — | — | — | 3.08 | |
| BARCOR + SDEvaluation Protocol=Offline Dataset2025.07 | 19.95 | 41.08 | — | — | — | — | 3.52 | |
| UniCRS + CRCRSEvaluation Protocol=Offline Dataset2025.07 | 19.91 | 40.6 | — | — | — | — | 3.76 | |
| MHIM2025.07 | 19.66 | 38.32 | 7.42 | 8.3 | 10.27 | 14.4 | — | |
| UniCRSEvaluation Protocol=Offline Dataset2025.07 | 19.6 | 40.5 | — | — | — | — | 3.53 | |
| BARCOR + CFCRSEvaluation Protocol=Offline Dataset2025.07 | 18.98 | 38.46 | — | — | — | — | 3.5 | |
| KGSF2022.01 | 18.3 | 37.8 | — | — | — | — | 3.9 | |
| KGConvRec2025.07 | 18.19 | 35.87 | 7.11 | 7.94 | 9.69 | 13.58 | — | |
| KBRD2025.07 | 17.96 | 34.21 | 7.22 | 8 | 9.72 | 13.33 | — | |
| KGSF2025.07 | 17.85 | 36.9 | 7.05 | 7.96 | 9.56 | 13.79 | — | |
| BARCOREvaluation Protocol=Offline Dataset2025.07 | 17.34 | 36.32 | — | — | — | — | 3.13 | |
| ReDial2025.07 | 17.05 | 30.77 | 6.77 | 7.38 | 9.25 | 12.22 | — | |
| BART2025.07 | 16.93 | 37.83 | 6.46 | 7.44 | 8.88 | 13.5 | — | |
| TG-ReDial2025.07 | 16.79 | 33.27 | 6.94 | 7.71 | 12.86 | — | — | |
| BERT2025.07 | 16.08 | 35.25 | 5.97 | 6.88 | 8.31 | 12.55 | — | |
| XLNet2025.07 | 15.69 | 35.9 | 5.83 | 6.77 | 8.11 | 12.55 | — | |
| KBRD2022.01 | 15 | 33.6 | — | — | — | — | 3.1 | |
| KECRS2022.01 | 14.3 | 34 | — | — | — | — | 2.1 | |
| ReDial2022.01 | 14 | 32 | — | — | — | — | 2.4 | |
| BERT4Rec2025.07 | 12.85 | 30.32 | 4.75 | 5.55 | 6.63 | 10.45 | — | |
| SASRec2025.07 | 11.17 | 23.29 | 5.4 | 5.93 | 6.74 | 9.36 | — | |
| TextCNN2022.01 | 6.8 | 19.1 | — | — | — | — | 1.3 | |
| TextCNN2025.07 | 6.44 | 18.21 | 2.35 | 2.85 | 3.28 | 5.8 | — | |
| Popularity2022.01 | 5.4 | 18.3 | — | — | — | — | 1.1 |