User Modeling on User Modeling star ratings
0.11MAESOCIA-EVO
Evaluation Results
| Method | Links | |
|---|---|---|
| SOCIA-EVOBackbone=GPT-5.1, Memory Update Policy=SOCIA-EVO2026.04 | 0.11 | |
| G-SIM-ESBackbone=GPT-5.1, Pipeline=Native2026.04 | 0.13 | |
| ACE-OLBackbone=GPT-5.1, Numerical Calibrator=Augmented2026.04 | 0.14 | |
| ReflexionBackbone=GPT-5.1, Numerical Calibrator=Augmented2026.04 | 0.17 | |
| G-SIM-SBIBackbone=GPT-5.1, Pipeline=Native2026.04 | 0.19 | |
| Yulan-OneSimBackbone=GPT-5.1, Pipeline=Native2026.04 | 0.21 | |
| DC-CUBackbone=GPT-5.1, Numerical Calibrator=Augmented2026.04 | 0.27 |