Text Clustering on Aggregate Suite (test)
82.2Macro AccuracyGold
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GoldModel=Qwen-2.5-72b-it, Prompt Order=T-C2024.06 | 82.2 | 83.8 | |
| GoldModel=Qwen-2.5-72b-it, Prompt Order=C-T2024.06 | 80 | 81.6 | |
| GoldModel=llama-3.1-8b-it, Prompt Order=T-C2024.06 | 71.7 | 71.2 | |
| ZeroDLModel=Qwen-2.5-72b-it, Prompt Order=T-C2024.06 | 70 | 69.4 | |
| ZeroDLModel=Qwen-2.5-72b-it, Prompt Order=C-T2024.06 | 68.1 | 67.5 | |
| KMeansModel=SBERT2024.06 | 65.6 | 67.5 | |
| GoldModel=llama-3.1-8b-it, Prompt Order=C-T2024.06 | 65.1 | 66.7 | |
| ZeroDLModel=llama-3.1-8b-it, Prompt Order=T-C2024.06 | 63.1 | 61.1 | |
| IDASModel=Qwen-2.5-72b-it, Prompt Order=T-C2024.06 | 62.7 | 61.7 | |
| IDASModel=Qwen-2.5-72b-it, Prompt Order=C-T2024.06 | 62.3 | 61.1 | |
| IDASModel=llama-3.1-8b-it, Prompt Order=T-C2024.06 | 56.4 | 56.2 | |
| ZeroDLModel=llama-3.1-8b-it, Prompt Order=C-T2024.06 | 53.4 | 53.2 | |
| IDASModel=llama-3.1-8b-it, Prompt Order=C-T2024.06 | 53.2 | 53.9 | |
| KMeansModel=TF-IDF2024.06 | 46.7 | 48.8 |