List your company

Dialogue Session Performance Analysis on MultiWOZ 1.0 (test)

13.7RAG CallsNo cache (baseline)
0.81444.15977.50510.8503Mar 22, 2026

Evaluation results

MethodLinks
No cache (baseline)Caching=None2026.0313.718,80000
Cosinetau=0.852026.037.29,9000143
CAS onlyMethod Components=Certified Answer Store2026.032.12,90000
CAS+PABMethod Components=Certified Answer Store + Pre-Answer Blocks, Coverage p=25%2026.031.891,24000
CAS+PABMethod Components=Certified Answer Store + Pre-Answer Blocks, Coverage p=50%2026.031.5272000
CAS+PABMethod Components=Certified Answer Store + Pre-Answer Blocks, Coverage p=75%2026.031.3848000
CAS+PABMethod Components=Certified Answer Store + Pre-Answer Blocks, Coverage p=100%2026.031.3134000