User Behavior Modeling on Alipay 10 Scenarios (test)
0.6678ActiveQ-Anchor (Prompt Tuned)
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Q-Anchor (Prompt Tuned)Embedding Category=Q-Anchor Embedding (Ours), Tuning Strategy=post-trained2026.02 | 0.6678 | 0.5844 | 0.8443 | 0.9716 | 0.9242 | 0.9439 | 0.8811 | 0.8535 | 0.635 | 0.9194 | 0.8225 | — | |
| One4allEmbedding Category=User Embedding Models2026.02 | 0.6515 | 0.5568 | 0.9509 | 0.9614 | 0.9203 | 0.8782 | 0.7609 | 0.6289 | 0.5761 | 0.8207 | 0.7706 | — | |
| CPCEmbedding Category=User Embedding Models2026.02 | 0.6506 | 0.5314 | 0.9506 | 0.9608 | 0.9171 | 0.8736 | 0.7817 | 0.6235 | 0.6101 | 0.8259 | 0.7725 | — | |
| MSDPEmbedding Category=User Embedding Models2026.02 | 0.6415 | 0.5155 | 0.9504 | 0.958 | 0.9152 | 0.8746 | 0.7814 | 0.6318 | 0.585 | 0.8389 | 0.7692 | — | |
| Q-Anchor (Base)Embedding Category=Q-Anchor Embedding (Ours), Tuning Strategy=pretrained2026.02 | 0.6368 | 0.5739 | 0.842 | 0.97 | 0.9218 | 0.9382 | 0.8799 | 0.7979 | 0.6189 | 0.9049 | 0.8104 | — | |
| FOUNDEmbedding Category=User Embedding Models2026.02 | 0.6201 | 0.5527 | 0.8131 | 0.9573 | 0.9083 | 0.9235 | 0.8528 | 0.7294 | 0.6202 | 0.8544 | 0.7832 | — | |
| Llama-Embed-Nemotron-8BEmbedding Category=General Embedding Models2026.02 | 0.5882 | 0.5627 | 0.7735 | 0.8372 | 0.8632 | 0.8708 | 0.8176 | 0.7525 | 0.5918 | 0.8303 | 0.7488 | — | |
| KaLM-Embed-Gemma2-9BEmbedding Category=General Embedding Models2026.02 | 0.5597 | 0.5359 | 0.7609 | 0.7729 | 0.8229 | 0.8174 | 0.7812 | 0.6564 | 0.589 | 0.7609 | 0.7058 | — | |
| Qwen2-Embedding-0.6BEmbedding Category=General Embedding Models2026.02 | 0.5378 | 0.5226 | 0.7294 | 0.7287 | 0.7106 | 0.7123 | 0.6914 | 0.6076 | 0.5508 | 0.7172 | 0.6508 | — | |
| Qwen2.5-0.5B-InstructEmbedding Category=General Embedding Models2026.02 | 0.5269 | 0.5173 | 0.7219 | 0.7161 | 0.6969 | 0.6885 | 0.6361 | 0.5855 | 0.5483 | 0.7134 | 0.6351 | — |