Recommendation on Netflix w/ history
4.027Performance ScoreShapE-GRPO
Evaluation results
| Method | Links | |
|---|---|---|
| ShapE-GRPOBackbone=LLAMA 3.1-8B-INSTRUCT, Training Algorithm=ShapE-GRPO2026.03 | 4.027 | |
| GRPOBackbone=LLAMA 3.1-8B-INSTRUCT, Training Algorithm=GRPO2026.03 | 3.783 | |
| LLAMA 3.1-8B-INSTRUCTBackbone=LLAMA 3.1-8B-INSTRUCT, Training Algorithm=Pretrained2026.03 | 1.885 |