Semantic Parsing on COGS (COGS EM)
95.84COGS EMLoRA-r16 + replay 10%
Evaluation results
| Method | Links | |
|---|---|---|
| LoRA-r16 + replay 10%Rank=16, Replay ratio=10%, Trainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 95.84 | |
| LoRA-r16 + replay 1%Rank=16, Replay ratio=1%, Trainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 95.52 | |
| LoRA-r16Rank=16, Trainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 95.44 | |
| FProj-LRTrainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 94.6 | |
| Fora-LRTrainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 94.48 | |
| OPLoRA-r16Rank=16, Trainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 94.44 | |
| CorDA-k16-r16Rank=16, k=16, Trainable parameters=~17M, Number of seeds=5, Backbone model=Qwen3-1.7B2026.06 | 94.16 |