Question Answering on ARC Challenging
15.65LLMcritic CallsVecCISC + KMeans
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VecCISC + KMeansBudget=20, Backbone=Mistral 7B, Cluster candidate selection=min-centroid2026.05 | 15.65 | -21.73 | |
| VecCISC + KMeansBudget=20, Backbone=Llama 3.1 8B, Cluster candidate selection=min-centroid2026.05 | 14.8 | -26 | |
| VecCISC + KMeansBudget=20, Backbone=GPT-4o mini, Cluster candidate selection=min-centroid2026.05 | 13.34 | -33.29 | |
| VecCISC + KMeansBudget=20, Backbone=Llama3.3 70B, Cluster candidate selection=min-centroid2026.05 | 13.31 | -33.43 | |
| VecCISC + KMeansBudget=20, Backbone=Qwen2.5 7B, Cluster candidate selection=min-centroid2026.05 | 10.94 | -45.3 |