Humorous Image Captioning on CLoT SYSU
68.3Win RateHUMORCHAIN (I)
Evaluation results
| Method | Links | |
|---|---|---|
| HUMORCHAIN (I)Strategy=Theory-Guided Multi-Stage Reasoning, Total Samples=794, Evaluation Protocol=Pairwise comparison vs External CLoT (G)2025.11 | 68.3 | |
| HUMORCHAIN (without discriminator) (J)Strategy=Theory-Guided Multi-Stage Reasoning (without discriminator), Total Samples=300, Evaluation Protocol=Pairwise comparison vs External CLoT (G)2025.11 | 62.6 | |
| External CLoT (SYSU) (G)Strategy=Sun Yat-sen University’s CLoT model, Total Samples=300, Evaluation Protocol=Pairwise comparison vs HUMORCHAIN (J)2025.11 | 37.4 | |
| External CLoT (SYSU) (G)Strategy=Sun Yat-sen University’s CLoT model, Total Samples=794, Evaluation Protocol=Pairwise comparison vs HUMORCHAIN (I)2025.11 | 31.7 |