GPT4-LLM
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Over-refusal evaluation | Poisoned GPT4-LLM subset | Informative Refusal Rate35.7 | 27 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Over-refusal evaluation | Poisoned GPT4-LLM subset | Informative Refusal Rate35.7 | 27 |