List your company
ResearchFormerly WizWand

Open-ended Question Answering on ANTIQUE (S5)

65.97Kendall's Tau (K)MinosEval
20.771632.505844.2455.9742Jun 18, 2025
Updated 8mo ago

Evaluation results

MethodLinks
MinosEvalmanual_classification=true2025.0665.9769.9184.7996.27
MinosEvalmanual_classification=false2025.0664.9368.8384.6996.19
Pairwisetype=Naive LLM Evaluation2025.0663.5368.9181.4595.46
Listwisetype=Naive LLM Evaluation2025.0662.5568.5683.395.93
LINKAGEtype=Others2025.0652.6557.7179.8995.17
Pointwisetype=Naive LLM Evaluation2025.0650.3655.9977.0894.42
BEMtype=LM-based Metrics2025.0639.7543.3776.3293.62
PEDANTStype=LM-based Metrics2025.0637.8541.4974.0393.18
BERTScoretype=LM-based Metrics2025.0629.5633.166.9492.02
BLEUtype=Automatic Metrics2025.0626.0829.0266.1591.85
ROUGE-Ltype=Automatic Metrics2025.0622.5125.4564.9491.59