Conversational Recommendation on INSPIRED (test)
10.6R@1KERL
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| KERL2023.12 | 10.6 | 28.1 | 43.9 | — | — | — | — | — | |
| SMTPO2026.04 | 9.9 | 27.3 | — | 17.4 | 14.2 | — | — | — | |
| MSCRS2026.04 | 9.6 | 25.7 | — | 16.8 | 14 | — | — | — | |
| DCRS2026.04 | 9.3 | 22.6 | — | 15.3 | 13 | — | — | — | |
| UniCRS2023.12 | 9.1 | 25 | 40.8 | — | — | — | — | — | |
| C2-CRS2023.12 | 8.9 | 24 | 38.2 | — | — | — | — | — | |
| UniCRS2026.04 | 8.5 | 23 | — | 14.9 | 12.5 | — | — | — | |
| GPT-4omode=zero-shot2026.04 | 7.9 | 19.6 | — | 12.1 | 9.8 | — | — | — | |
| HARPO2026.04 | 7.2 | 27.4 | 48.8 | 19.4 | 14.2 | 66 | 62 | 0.454 | |
| KGSF2023.12 | 6.4 | 17.5 | 27.3 | — | — | — | — | — | |
| KBRD2023.12 | 5.8 | 17.2 | 26.5 | — | — | — | — | — | |
| GPT-3.5mode=zero-shot2026.04 | 5.3 | 17.7 | — | 10.9 | 8.8 | — | — | — | |
| KGSF2026.04 | 5.1 | 13.2 | — | 9.2 | 7.9 | — | — | — | |
| BERT2026.04 | 4.9 | 18.9 | — | 11.2 | 8.8 | — | — | — | |
| RecMind2026.04 | 4.8 | 20.4 | 41.2 | 14 | 10.2 | 52 | 48 | 0.37 | |
| TextCNN2023.12 | 4.7 | 16.1 | 32.7 | — | — | — | — | — | |
| TREA2026.04 | 4.7 | 14.6 | — | 9.5 | 7.6 | — | — | — | |
| BERT2023.12 | 4.4 | 17.9 | 32.8 | — | — | — | — | — | |
| L3.1-8B-Imode=zero-shot2026.04 | 4.3 | 16.2 | — | 9.7 | 7.7 | — | — | — | |
| VRICR2026.04 | 4.3 | 14.1 | — | 9.1 | 7.5 | — | — | — | |
| KBRD2026.04 | 4.2 | 13.5 | — | 8.8 | 7.3 | — | — | — | |
| GPT-42026.04 | 4.2 | 18.8 | 39.4 | 12.9 | 9.4 | 53 | 49 | 0.358 | |
| UniCRS2026.04 | 3.8 | 17.6 | 37.2 | 11.8 | 8.6 | 48 | 44 | 0.331 | |
| Popularity2023.12 | 3.2 | 15.5 | 32.3 | — | — | — | — | — | |
| Popularity2026.04 | 3.1 | 15.5 | — | 8.5 | 6.4 | — | — | — | |
| ReDial2023.12 | 3 | 11.7 | 28.5 | — | — | — | — | — | |
| KGSF2026.04 | 2.4 | 13.8 | 31.6 | 8.8 | 6.4 | 40 | 36 | 0.27 | |
| ReDial2026.04 | 0.9 | 4.8 | — | 2.3 | 1.5 | — | — | — | |
| Llama2 + FNSCRSEvaluation Protocol=User Simulator2025.07 | 0.3478 | 0.5776 | 0.7329 | — | — | — | — | — | |
| Llama2 + CRCRSEvaluation Protocol=User Simulator2025.07 | 0.2609 | 0.3975 | 0.5155 | — | — | — | — | — | |
| BARCOR + FNSCRSEvaluation Protocol=User Simulator2025.07 | 0.2484 | 0.4037 | 0.6149 | — | — | — | — | — | |
| Llama2 + SDEvaluation Protocol=User Simulator2025.07 | 0.2422 | 0.354 | 0.4223 | — | — | — | — | — | |
| UniCRS + SDEvaluation Protocol=User Simulator2025.07 | 0.1553 | 0.2484 | 0.4099 | — | — | — | — | — | |
| BARCOR + CFCRSEvaluation Protocol=User Simulator2025.07 | 0.1491 | 0.2422 | 0.3727 | — | — | — | — | — | |
| UniCRS + CRCRSEvaluation Protocol=User Simulator2025.07 | 0.1491 | 0.236 | 0.4099 | — | — | — | — | — | |
| UniCRS + FNSCRSEvaluation Protocol=User Simulator2025.07 | 0.1366 | 0.2981 | 0.4534 | — | — | — | — | — | |
| Llama2 + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0932 | 0.2826 | 0.5093 | — | — | — | — | — | |
| BARCOR + SDEvaluation Protocol=User Simulator2025.07 | 0.0807 | 0.2795 | 0.354 | — | — | — | — | — | |
| UniCRSEvaluation Protocol=User Simulator2025.07 | 0.0807 | 0.236 | 0.4037 | — | — | — | — | — | |
| UniCRS + CRCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0755 | 0.2278 | 0.4424 | — | — | — | — | — | |
| UniCRS + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0543 | 0.2291 | 0.3947 | — | — | — | — | — | |
| Llama2 + CRCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0522 | 0.1935 | 0.3739 | — | — | — | — | — | |
| Llama2Evaluation Protocol=User Simulator2025.07 | 0.0497 | 0.1242 | 0.3478 | — | — | — | — | — | |
| BARCOR + CFCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0472 | 0.205 | 0.3516 | — | — | — | — | — | |
| Llama2 + SDEvaluation Protocol=Offline Dataset2025.07 | 0.0472 | 0.2584 | 0.4075 | — | — | — | — | — | |
| UniCRS + SDEvaluation Protocol=Offline Dataset2025.07 | 0.0464 | 0.2053 | 0.3894 | — | — | — | — | — | |
| Llama2Evaluation Protocol=Offline Dataset2025.07 | 0.0446 | 0.1168 | 0.3416 | — | — | — | — | — | |
| UniCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0397 | 0.2 | 0.4066 | — | — | — | — | — | |
| BARCOR + FNSCRSEvaluation Protocol=Offline Dataset2025.07 | 0.0373 | 0.2112 | 0.4311 | — | — | — | — | — | |
| BARCOREvaluation Protocol=User Simulator2025.07 | 0.0373 | 0.1367 | 0.3043 | — | — | — | — | — | |
| BARCOREvaluation Protocol=Offline Dataset2025.07 | 0.0286 | 0.1106 | 0.3081 | — | — | — | — | — | |
| BARCOR + SDEvaluation Protocol=Offline Dataset2025.07 | 0.0248 | 0.1938 | 0.3578 | — | — | — | — | — |