Delusion Type Classification on ADAPT N=122 (test)
77.9Micro-F1Majority Vote
Evaluation Results
| Method | Links | |
|---|---|---|
| Majority VotePrompt Level=Level 4 (Full Prompt)2026.05 | 77.9 | |
| GLM-4.6Prompt Level=Level 4 (Full Prompt)2026.05 | 77.7 | |
| Direct JudgePrompt Level=Level 4 (Full Prompt)2026.05 | 77.5 | |
| DebatePrompt Level=Level 4 (Full Prompt)2026.05 | 76.5 | |
| GPT-OSSPrompt Level=Level 4 (Full Prompt)2026.05 | 76.2 | |
| Majority VotePrompt Level=Level 1 (Category)2026.05 | 74.6 | |
| Qwen-3Prompt Level=Level 4 (Full Prompt)2026.05 | 73.6 | |
| GLM-4.6Prompt Level=Level 1 (Category)2026.05 | 70.7 | |
| Qwen-3Prompt Level=Level 1 (Category)2026.05 | 66.7 | |
| GPT-OSSPrompt Level=Level 1 (Category)2026.05 | 64.9 |