Context Extraction on CoQA
88.1AccuracyBERT-Judge
Evaluation results
| Method | Links | |
|---|---|---|
| BERT-Judgeclean_name=BERT-as-a-Judge2026.04 | 88.1 | |
| LLM-Judgebackbone=Qwen-3 0.6B2026.04 | 75.2 | |
| Regex2026.04 | 67 |
| Method | Links | |
|---|---|---|
| BERT-Judgeclean_name=BERT-as-a-Judge2026.04 | 88.1 | |
| LLM-Judgebackbone=Qwen-3 0.6B2026.04 | 75.2 | |
| Regex2026.04 | 67 |