Factuality Detection on CSQA (test)
74.8AUROCTraceDet
Evaluation Results
| Method | Links | |
|---|---|---|
| TraceDetSource Dataset=TriviaQA, Method Category=Trajectory-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 74.8 | |
| DynHDSource Dataset=TriviaQA, Method Category=Trajectory-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 73.6 | |
| DynHDSource Dataset=HotpotQA, Method Category=Trajectory-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 71.4 | |
| TraceDetSource Dataset=HotpotQA, Method Category=Trajectory-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 66.2 | |
| TSVSource Dataset=HotpotQA, Method Category=Latent-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 63.2 | |
| CCSSource Dataset=HotpotQA, Method Category=Latent-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 56.6 | |
| TSVSource Dataset=TriviaQA, Method Category=Latent-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 56.2 | |
| CCSSource Dataset=TriviaQA, Method Category=Latent-based, Evaluation Protocol=Zero-shot cross-task generalization2026.03 | 54.2 |