Benchmark Ranking Prediction on TruthfulQA
0.605Kendall's Tau CorrelationABLE
Evaluation results
| Method | Links | |
|---|---|---|
| ABLE2026.04 | 0.605 | |
| Log-Likelihood2026.04 | 0.476 | |
| PhyloLM2026.04 | 0.26 |
| Method | Links | |
|---|---|---|
| ABLE2026.04 | 0.605 | |
| Log-Likelihood2026.04 | 0.476 | |
| PhyloLM2026.04 | 0.26 |