Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Irrelevant Classification on JD search logs 1.0 (test)
Loading...
92.42
Precision
LLM Base
89.5496
90.2948
91.04
91.7852
Apr 28, 2026
Precision
Recall
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
LLM Base
Backbone=Qwen3-8B, Mod...
2026.04
92.42
39.72
55.56
K-CARE w/ SCA (QSAP)
Framework=Symmetrical...
2026.04
90.7
90.78
90.74
K-CARE w/ SCA + APR (Proposed)
Framework=SCA + Analog...
2026.04
90.68
91.51
91.09
K-CARE w/ SCA (QSAP+PSAQ)
Framework=Symmetrical...
2026.04
90.61
91.07
90.84
K-CARE w/ SCA (QSAP+PSAQ+TGKI)
Framework=Symmetrical...
2026.04
90.49
91.5
90.99
LLM SFT
Backbone=Qwen3-8B, Mod...
2026.04
89.91
90.3
90.11
LLM GRPO
Backbone=Qwen3-8B, Mod...
2026.04
89.66
91.3
90.48
Feedback
Search any
task
Search any
task