Hallucination Detection on CoQA (Accuracy)
79.19AccuracyVal Loss
Evaluation Results
| Method | Links | |
|---|---|---|
| Val LossModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 79.19 | |
| IDModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 79.19 | |
| FEPoIDModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 79.19 | |
| CurvatureModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 77.37 | |
| SNRModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 76.39 | |
| IDModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 73.56 | |
| FEPoIDModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 73.56 | |
| Val LossModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 73.29 | |
| CurvatureModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 71.9 | |
| SNRModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 68.59 | |
| RGNModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 67.86 | |
| RGNModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 64.21 | |
| RankMEModel=LlaMA-3.2-3B, Forward horizon (w)=7, Representation extraction (FST)=true2026.05 | 62.65 | |
| RankMEModel=LlaMA-3.2-1B, Forward horizon (w)=3, Representation extraction (FST)=true2026.05 | 58.13 |