List your company

Question Answering on ARC Challenge (NLL)

0.47NLLPPT (Distribution) + TS
0.44960.58730.7250.8627May 26, 2026

Evaluation results

MethodLinks
PPT (Distribution) + TSBackbone=QWEN2-7B, Temperature Scaling=true2026.050.47
Base + TSBackbone=QWEN2-7B, Temperature Scaling=true2026.050.49
PPT (Distribution)Backbone=QWEN2-7B, Temperature Scaling=false2026.050.51
PPT (Distribution) + TSBackbone=LLAMA3-8B, Temperature Scaling=true2026.050.6
PPT (Distribution)Backbone=LLAMA3-8B, Temperature Scaling=false2026.050.61
Base + TSBackbone=LLAMA3-8B, Temperature Scaling=true2026.050.62
PPT (Mean)Backbone=LLAMA3-8B, Temperature Scaling=false2026.050.74
PPT (Mean)Backbone=QWEN2-7B, Temperature Scaling=false2026.050.76
BaseBackbone=QWEN2-7B, Temperature Scaling=false2026.050.9
BaseBackbone=LLAMA3-8B, Temperature Scaling=false2026.050.98