MultiWOZ, Super-NaturalInstructions, TruthfulQA, and Self-Instruct
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Structured JSON Generation | MultiWOZ, Super-NaturalInstructions, TruthfulQA, and Self-Instruct Averaged | Similarity Score0.88 | 16 |
Showing 1 of 1 rows