Sentence-level Error Detection on HQ2A 1.0 (test)
25.49Exact AccuracyGPT-3.5-Turbo
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-3.5-TurboApproach=Zero-shot2024.07 | 25.49 | 11.76 | 62.75 | 37.65 | 0.99 |
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-3.5-TurboApproach=Zero-shot2024.07 | 25.49 | 11.76 | 62.75 | 37.65 | 0.99 |