Causal and temporal relations assessment on DementiaBank (manual transcripts)
2.02Control Mean4o-mini
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| 4o-miniModel Version=GPT-4o-mini, Transcript type=Manual2026.06 | 2.02 | 2.12 | 0.05 | 0.3 | 0.27 | 0.02 | 0.08 | |
| 4oModel Version=GPT-4o, Transcript type=Manual2026.06 | 1.79 | 2.25 | 0.26 | 0.57 | 0.41 | 0.42 | 0.25 | |
| LLaMAModel Version=Llama 3 70B, Transcript type=Manual2026.06 | 1.68 | 2.04 | 0.21 | 0.29 | 0.22 | 0.02 | 0.49 | |
| ClaudeModel Version=Claude 3.5 Sonnet, Transcript type=Manual2026.06 | 1.06 | 1.75 | 0.66 | 0.71 | 0.5 | 0.43 | 0.5 |