Spoken Summarization on MCIF long track
29.74BERTScoreChain-of-Thought (CoT)
Evaluation results
| Method | Links | |
|---|---|---|
| Chain-of-Thought (CoT)Prompt Evaluation Mode=Mixed2026.06 | 29.74 | |
| N2+IT+AvgPrompt Evaluation Mode=Mixed2026.06 | 29.41 | |
| N2+AvgPrompt Evaluation Mode=Mixed2026.06 | 29.33 | |
| N2Prompt Evaluation Mode=Fixed2026.06 | 29.05 | |
| Temp. Sampling (T = 2)Prompt Evaluation Mode=Mixed2026.06 | 28.99 | |
| Temp. Sampling (T = 2)Prompt Evaluation Mode=Fixed2026.06 | 28.87 | |
| Fixed-Prob. SamplingPrompt Evaluation Mode=Fixed2026.06 | 28.77 | |
| Fixed-Prob. SamplingPrompt Evaluation Mode=Mixed2026.06 | 28.76 | |
| N2Prompt Evaluation Mode=Mixed2026.06 | 28.75 | |
| Cascaded+FT (Contrastive)Prompt Evaluation Mode=Fixed2026.06 | 28.55 | |
| Cascaded+FT (Contrastive)Prompt Evaluation Mode=Mixed2026.06 | 27.33 | |
| Chain-of-Thought (CoT)Prompt Evaluation Mode=Fixed2026.06 | 26.56 | |
| N2+IT+AvgPrompt Evaluation Mode=Fixed2026.06 | 26.1 | |
| N2+AvgPrompt Evaluation Mode=Fixed2026.06 | 26.06 | |
| Qwen 2.5 OmniPrompt Evaluation Mode=Mixed2026.06 | 17.87 | |
| Qwen 2.5 OmniPrompt Evaluation Mode=Fixed2026.06 | 14.21 | |
| CascadedPrompt Evaluation Mode=Mixed2026.06 | 13.4 | |
| CascadedPrompt Evaluation Mode=Fixed2026.06 | 13.31 | |
| N2+IT+SHASPrompt Evaluation Mode=Mixed2026.06 | 5.9 | |
| N2+IT+SHASPrompt Evaluation Mode=Fixed2026.06 | 2.93 |