Affective Response Classification on ADAPT N=122 (test)
83.9Micro-averaged F1Majority Vote
Evaluation Results
| Method | Links | |
|---|---|---|
| Majority VotePrompt Level=Level 1 (Category)2026.05 | 83.9 | |
| Qwen-3Prompt Level=Level 1 (Category)2026.05 | 81.3 | |
| Majority VotePrompt Level=Level 4 (Full Prompt)2026.05 | 80 | |
| GLM-4.6Prompt Level=Level 1 (Category)2026.05 | 79.7 | |
| GPT-OSSPrompt Level=Level 1 (Category)2026.05 | 77.4 | |
| Qwen-3Prompt Level=Level 4 (Full Prompt)2026.05 | 76.8 | |
| GPT-OSSPrompt Level=Level 4 (Full Prompt)2026.05 | 76 | |
| Direct JudgePrompt Level=Level 4 (Full Prompt)2026.05 | 73.8 | |
| DebatePrompt Level=Level 4 (Full Prompt)2026.05 | 71.9 | |
| GLM-4.6Prompt Level=Level 4 (Full Prompt)2026.05 | 69.4 |