Query Categorization on AI pseudo-reference dataset OpenAI-GPT-4o-Mini
132.1F1 Score (Scaled)CoT BFS
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| CoT BFSAggregation type=Sample aggregation, Select-threshold=9, min-threshold=82026.01 | 132.1 | — | — | — | 89.8 | 3.7 | |
| CoT BFSAggregation type=Macro aggregation, Select-threshold=9, min-threshold=82026.01 | 112.1 | — | — | — | 47.8 | 111.4 | |
| CoT BFSAggregation type=Micro Aggregation, Select-threshold=9, min-threshold=82026.01 | 96.7 | — | — | — | 137.5 | -5.4 |