List your company

Generative Question Answering on TruthfulQA (test)

82.33HALL ScorePlan-and-Solve
65.242869.678974.11578.5511May 30, 2026

Evaluation results

MethodLinks
Plan-and-SolveBackbone=Llama 3.1-8b2026.0582.33512.6712.99
BaseBackbone=Llama 3.1-8b2026.0576.51.3822.1222.27
EmoPrompt (avg)Backbone=Llama 3.1-8b2026.0575.663.2321.1121.46
Append-idkBackbone=Llama 3.1-8b2026.0573.275.9920.7421.38
Plan-and-SolveBackbone=Gemma-3-12b-pt2026.0572.6712.6714.6715.66
RCSPBackbone=Llama 3.1-8b2026.0571.433.6924.8825.35
Append-idkBackbone=Gemma-3-12b-pt2026.0569.597.3723.0423.92
BaseBackbone=Gemma-3-12b-pt2026.0567.741.3830.8831.09
EmoPrompt (avg)Backbone=Gemma-3-12b-pt2026.0567.285.6127.1127.89
RCSPBackbone=Gemma-3-12b-pt2026.0565.92.7731.3331.77