Confidence Shift Estimation on Translation Student Task Competitive Setting
15Average Proportion Shift (Pedagogical)APV
Evaluation results
| Method | Links | ||
|---|---|---|---|
| APVPrompt=Direct2026.07 | 15 | 39 | |
| GPT-4oPrompt=Direct2026.07 | 19 | 33 | |
| Claude 3.5 SonnetPrompt=Direct2026.07 | 22 | 38 | |
| APVPrompt=CoT2026.07 | 28 | 66 | |
| GPT-4oPrompt=CoT2026.07 | 31 | 58 | |
| Claude 3.5 SonnetPrompt=CoT2026.07 | 35 | 61 |