Instruction Hierarchy
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Phrase Protection | Instruction Hierarchy (test) | User Message Protection Accuracy97.5 | 4 | |
| System Prompt Extraction | Instruction Hierarchy (test) | Attack Success Rate (Realistic User)99.7 | 4 |
Showing 2 of 2 rows