ConFiQA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Open-book generation under knowledge conflict | ConFiQA 1,500 subset | Ps Score81.07 | 32 | |
| Context-faithful Question Answering | ConFiQA | MR13.21 | 24 | |
| Retrieval Following | ConFiQA MC 1.0 (test) | Pc54.9 | 20 | |
| Retrieval Following | ConFiQA MR 1.0 (test) | Pc61.2 | 20 | |
| Retrieval Following | ConFiQA QA 1.0 (test) | Pc92.3 | 20 | |
| Open-book generation under knowledge conflict | ConFiQA MR 1,500 | Ps Score59.8 | 16 | |
| Question Answering | ConFiQA (out-of-domain) | Hit84.63 | 12 | |
| Context-faithful Reasoning | ConFiQA MC | Pc38.8 | 8 | |
| Context-faithful Multi-hop Reasoning | ConFiQA MR | Pc45.4 | 8 | |
| Question Answering | ConFiQA-QA counterfactual contexts | Accuracy81.2 | 7 | |
| Multiple Choice | ConFiQA MC | Ps Score53.4 | 4 | |
| Machine Reading | ConFiQA MR | Ps Score54.47 | 4 | |
| Question Answering | ConFiQA QA | Ps74.73 | 4 |
Showing 13 of 13 rows