Event Attribution on Turing Change Point Dataset Suite (7 datasets) (test)
67Explanation AccuracyLlama 3.1 8B
Evaluation results
| Method | Links | |
|---|---|---|
| Llama 3.1 8BDetection Method=Ensemble2026.01 | 67 | |
| DeepSeek-R1Detection Method=Ensemble2026.01 | 67 | |
| Overall (Average)Detection Method=Ensemble2026.01 | 56 | |
| GPT-4oDetection Method=Individual2026.01 | 33 | |
| GPT-4oDetection Method=Ensemble2026.01 | 33 | |
| Llama 3.1 8BDetection Method=Individual2026.01 | 33 | |
| DeepSeek-R1Detection Method=Individual2026.01 | 33 | |
| Overall (Average)Detection Method=Individual2026.01 | 33 |