User-aligned task completion on KitchenAmbig (In-Distribution)
84AccuracyAdaptive CLIPR
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive CLIPRLLM engine=Claude Sonnet 4.5, alpha=1.5, f=52026.05 | 84 | |
| GATELLM engine=Claude Sonnet 4.52026.05 | 69.5 | |
| CIPHERLLM engine=Claude Sonnet 4.52026.05 | 61.4 |