Complex Query Answering on NELL-995 (test)
83.3Hits@1 (1p)ROG
Evaluation Results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ROGBase LLM=ChatGLM2026.02 | 83.3 | — | — | — | 59.2 | 41.5 | 61.1 | 58.7 | 50.1 | 42.9 | 62.2 | 57.2 | — | — | — | — | — | |
| CQDType=Embedding-based2026.02 | 66.4 | — | — | — | 32.7 | 26.8 | 55.8 | 51.2 | 33.6 | 37.7 | 45.4 | 39.2 | — | — | — | — | — | |
| CKGC2024.09 | 61.4 | 35.3 | — | 19.9 | 25.7 | 24.1 | 45.8 | 58.8 | 33.9 | 29.2 | 20.5 | 18.7 | 19.8 | 27.5 | 20.4 | 17.4 | 14.6 | |
| QTO2024.09 | 60.7 | 32.9 | — | 12.9 | 24.1 | 21.6 | 42.5 | 55.3 | 31.3 | 26.5 | 20.4 | 17.9 | 13.8 | 17.9 | 16.9 | 9.9 | 5.9 | |
| CQD-COoptimization=continuous2023.01 | 60.4 | 28.8 | — | — | 17.8 | 12.7 | 39.3 | 46.6 | 30.1 | 22 | 17.3 | 13.2 | — | — | — | — | — | |
| CQD-Beamoptimization=beam search2023.01 | 60.4 | 28.6 | — | — | 20.6 | 11.6 | 39.3 | 46.6 | 25.4 | 23.9 | 17.5 | 12.2 | — | — | — | — | — | |
| CQD^Acalibration=adapter-based2023.01 | 60.4 | 32.3 | — | 13.3 | 22.9 | 16.7 | 43.4 | 52.6 | 32.1 | 26.4 | 20 | 17 | 15.1 | 18.6 | 15.8 | 10.7 | 6.5 | |
| CQD-COvariant=CO2024.09 | 60.4 | 28.8 | — | — | 17.8 | 12.7 | 39.3 | 46.6 | 30.1 | 22 | 17.3 | 13.2 | — | — | — | — | — | |
| CQD-Beamvariant=Beam2024.09 | 60.4 | 28.6 | — | — | 20.6 | 11.6 | 39.3 | 50.6 | 25.4 | 18.6 | 15.8 | 12.9 | — | — | — | — | — | |
| CQDA2024.09 | 60.4 | 32.3 | — | 13.3 | 22.9 | 16.7 | 42.4 | 52.5 | 32.1 | 26.4 | 20 | 17 | 15.1 | 23.9 | 17.5 | 12.2 | 10.7 | |
| GNN-QE2023.01 | 53.3 | 28.9 | — | 9.7 | 18.9 | 14.9 | 42.4 | 52.5 | 30.8 | 18.9 | 15.9 | 12.6 | 9.9 | 14.6 | 11.4 | 6.3 | 6.3 | |
| GNN-QE2024.09 | 53.3 | 28.9 | — | 9.7 | 18.9 | 14.9 | 43.4 | 52.6 | 30.8 | 18.9 | 15.9 | 12.6 | 9.9 | 14.6 | 11.4 | 6.3 | 6.3 | |
| ConE2023.01 | 53.1 | 27.2 | — | 6.4 | 16.1 | 13.9 | 40 | 50.8 | 26.3 | 17.5 | 15.3 | 11.3 | 5.7 | 8.1 | 10.8 | 3.5 | 3.9 | |
| ConE2024.09 | 53.1 | 27.2 | — | 6.4 | 16.1 | 13.9 | 40 | 50.8 | 26.3 | 17.5 | 15.3 | 11.3 | 5.7 | 8.1 | 10.8 | 3.5 | 3.9 | |
| Q2BType=Embedding-based2026.02 | 53.1 | — | — | — | 31 | 22.4 | 51.4 | 46.9 | 29.1 | 31.1 | 37.6 | 21.5 | — | — | — | — | — | |
| BetaE2023.01 | 53 | 24.6 | — | 5.9 | 13 | 11.4 | 37.6 | 47.5 | 24.1 | 14.3 | 12.2 | 8.5 | 5.1 | 7.8 | 10 | 3.1 | 3.5 | |
| BetaE2024.09 | 53 | 24.6 | — | 5.9 | 13 | 11.4 | 37.6 | 47.5 | 24.1 | 14.3 | 12.2 | 8.5 | 5.1 | 7.8 | 10 | 3.1 | 3.5 | |
| GQEType=Embedding-based2026.02 | 52.5 | — | — | — | 29.5 | 15.3 | 35.6 | 38.8 | 25.4 | 28.5 | 26.9 | 18.6 | — | — | — | — | — | |
| QTO2022.12 | 51.6 | 24.8 | 16.7 | 6.1 | 17.1 | 15.3 | 32.1 | 40.8 | 23.1 | 19.9 | 12.3 | 11.3 | 5.6 | 9.4 | 9.9 | 3.5 | 2.1 | |
| CQDvariant=CO2022.12 | 51.2 | 21.3 | 13.9 | — | 11.8 | 9 | 28.4 | 36.3 | 22.4 | 15.5 | 9.9 | 7.6 | — | — | — | — | — | |
| CQDvariant=Beam2022.12 | 51.2 | 21 | 13.2 | — | 14.3 | 6.3 | 28.4 | 36.3 | 18.1 | 17.4 | 10.2 | 7.2 | — | — | — | — | — | |
| CQDsearch=CO2026.02 | 51.2 | 21.3 | — | — | 11.8 | 9 | 28.4 | 36.3 | 22.4 | 15.5 | 9.9 | 7.6 | — | — | — | — | — | |
| CQDsearch=Beam2026.02 | 51.2 | 21 | — | — | 14.3 | 6.3 | 28.4 | 36.3 | 18.1 | 17.4 | 10.2 | 7.2 | — | — | — | — | — | |
| FuzzQE2024.09 | 47.4 | 27 | — | 7.8 | 17.2 | 14.6 | 39.5 | 49.2 | 26.2 | 20.6 | 15.3 | 12.6 | 7.8 | 9.8 | 11.1 | 4.9 | 5.5 | |
| ConE2022.12 | 43.6 | 19.8 | 11.6 | 2.2 | 10.7 | 9 | 28.6 | 39.8 | 19.2 | 11.4 | 9 | 6.6 | 1.4 | 2.6 | 5.2 | 0.8 | 1.2 | |
| BetaE2022.12 | 43.5 | 17.8 | 9.6 | 2.1 | 8.1 | 7 | 27.2 | 36.5 | 17.4 | 9.3 | 6.9 | 4.7 | 1.6 | 2.2 | 4.8 | 0.7 | 1.2 | |
| GNN-QE2022.12 | 43.5 | 21.5 | 13.2 | 3.6 | 12.9 | 9.9 | 32.5 | 42.4 | 23.5 | 12.9 | 8.8 | 7.4 | 3.2 | 5.9 | 5.4 | 1.6 | 2 | |
| BetaE2026.02 | 43.5 | 17.8 | — | 2.1 | 8.1 | 7 | 27.2 | 36.5 | 17.4 | 9.3 | 6.9 | 4.7 | 1.6 | 2.2 | 4.8 | 0.7 | 1.2 | |
| HYQNET2026.02 | 42.3 | 21.5 | — | 3.7 | 12 | 8.4 | 28.6 | 39.4 | 21.1 | 12.1 | 7.7 | 5.4 | 3.1 | 4.6 | 8.1 | 0.9 | 1.9 | |
| Q2B2023.01 | 42.2 | 22.9 | — | — | 14 | 11.2 | 33.3 | 44.5 | 22.4 | 16.8 | 11.3 | 10.3 | — | — | — | — | — | |
| Q2B2024.09 | 42.2 | 22.9 | — | — | 14 | 11.2 | 33.3 | 44.5 | 22.4 | 16.8 | 11.3 | 10.3 | — | — | — | — | — | |
| GNN-QE2026.02 | 41 | 21.5 | — | 3.3 | 12.4 | 9.3 | 29.2 | 40 | 20.2 | 11.7 | 8.2 | 6.4 | 2.5 | 5.3 | 5.5 | 1.5 | 1.7 | |
| GQE2023.01 | 32.8 | 18.6 | — | — | 11.9 | 9.6 | 27.5 | 35.2 | 18.4 | 14.4 | 8.5 | 8.8 | — | — | — | — | — | |
| GQE2024.09 | 32.8 | 18.6 | — | — | 11.9 | 9.6 | 27.5 | 35.2 | 18.4 | 14.4 | 8.5 | 8.8 | — | — | — | — | — | |
| Query2Box2022.12 | 23.8 | 14.1 | 8.8 | — | 8.7 | 6.9 | 20.3 | 31.5 | 14.3 | 10.7 | 5 | 6 | — | — | — | — | — | |
| Q2B2026.02 | 23.8 | 14.1 | — | — | 8.7 | 6.9 | 20.3 | 31.5 | 14.3 | 10.7 | 5 | 6 | — | — | — | — | — | |
| GQE2022.12 | 15.4 | 9.9 | 6.9 | — | 6.7 | 5 | 14.3 | 20.4 | 10.6 | 9 | 2.9 | 5 | — | — | — | — | — | |
| GQE2026.02 | 15.4 | 9.9 | — | — | 6.7 | 5 | 14.3 | 20.4 | 10.6 | 9 | 2.9 | 5 | — | — | — | — | — |