Binary Inconsistency Detection on FT-Summ (Accuracy)
75.61AccuracyChatGPT-SpanMoE
Evaluation Results
| Method | Links | |
|---|---|---|
| ChatGPT-SpanMoESetting=Few-Shot2024.06 | 75.61 | |
| ChatGPT-SpanMoESetting=Zero-Shot2024.06 | 73.77 | |
| ChatGPT-SpanSetting=Zero-Shot2024.06 | 73.48 | |
| ChatGPT-DASetting=Zero-Shot2024.06 | 73 | |
| ChatGPT-SpanSetting=Few-Shot2024.06 | 72.18 | |
| ChatGPT-DASetting=Few-Shot2024.06 | 72.06 | |
| SummaC-Conv2024.06 | 51.18 | |
| QuestEval2024.06 | 47.54 | |
| QAFactEval2024.06 | 45 | |
| SummaCSetting=Zero-Shot2024.06 | 43.29 |