List your company

Generative Question Answering on HaluEval (test)

50.33HALL RatePlan-and-Solve
49.817253.278656.7460.2014May 30, 2026

Evaluation results

MethodLinks
Plan-and-SolveBackbone=Llama 3.1-8b2026.0550.3317.673235.1
Append-idkBackbone=Gemma-3-12b-pt2026.0554.679.333637.76
RCSPBackbone=Gemma-3-12b-pt2026.055563940.21
EmoPrompt (avg)Backbone=Gemma-3-12b-pt2026.0555.798.7335.4837.1
Plan-and-SolveBackbone=Gemma-3-12b-pt2026.0556.675.6737.6738.77
BaseBackbone=Gemma-3-12b-pt2026.055843838.77
BaseBackbone=Llama 3.1-8b2026.0559.676.333435.11
Append-idkBackbone=Llama 3.1-8b2026.05604.3335.6736.46
RCSPBackbone=Llama 3.1-8b2026.0560.671.333838.26
EmoPrompt (avg)Backbone=Llama 3.1-8b2026.0563.156.6730.1831.25