List your company
ResearchFormerly WizWand

Question Answering on UNQOVER

99.75AccuracyCAL
3.321228.355653.3978.4244Apr 20, 2025
Updated 8mo ago

Evaluation results

MethodLinks
CALBackbone=Llama3-8B, Setting=Zero-shot2025.0499.75
CALBackbone=Llama3-8B, Setting=Few-shot2025.0495.67
FairSteerBackbone=Llama3-8B, Setting=Few-shot2025.0491.94
CALBackbone=Mistral-7B, Setting=Few-shot2025.0487.02
Llama3-8BSetting=Few-shot2025.0476.22
FairSteerBackbone=Vicuna-13B, Setting=Few-shot2025.0473.19
FairSteerBackbone=Mistral-7B, Setting=Few-shot2025.0469.51
CALBackbone=Mistral-7B, Setting=Zero-shot2025.0467.54
CALBackbone=Llama2-7B, Setting=Zero-shot2025.0462.52
CALBackbone=Llama2-13B, Setting=Zero-shot2025.0460.32
CALBackbone=Vicuna-13B, Setting=Few-shot2025.0458.76
FairSteerBackbone=Llama3-8B, Setting=Zero-shot2025.0458.01
Mistral-7BSetting=Few-shot2025.0457.83
FairSteerBackbone=Vicuna-7B, Setting=Few-shot2025.0457.21
FairSteerBackbone=Mistral-7B, Setting=Zero-shot2025.0454.1
FairSteerBackbone=Llama2-13B, Setting=Zero-shot2025.0453
Vicuna-13BSetting=Few-shot2025.0452.9
FairSteerBackbone=Llama2-13B, Setting=Few-shot2025.0449.23
FairSteerBackbone=Vicuna-13B, Setting=Zero-shot2025.0449.06
FairSteerBackbone=Vicuna-7B, Setting=Zero-shot2025.0443.11
Vicuna-13BSetting=Zero-shot2025.0441.44
CALBackbone=Vicuna-13B, Setting=Zero-shot2025.0435.34
Llama2-13BSetting=Zero-shot2025.0433.96
CALBackbone=Vicuna-7B, Setting=Zero-shot2025.0433.66
Mistral-7BSetting=Zero-shot2025.0433.06
CALBackbone=Llama2-13B, Setting=Few-shot2025.0432.27
FairSteerBackbone=Llama2-7B, Setting=Few-shot2025.0428.52
Llama3-8BSetting=Zero-shot2025.0420.84
Llama2-7BSetting=Few-shot2025.0420.6
FairSteerBackbone=Llama2-7B, Setting=Zero-shot2025.0419.67
Llama2-13BSetting=Few-shot2025.0419.17
Vicuna-7BSetting=Few-shot2025.0418.34
Vicuna-7BSetting=Zero-shot2025.0416.19
CALBackbone=Llama2-7B, Setting=Few-shot2025.0412.3
CALBackbone=Vicuna-7B, Setting=Few-shot2025.0410.88
Llama2-7BSetting=Zero-shot2025.047.03