List your company

Question Answering on BioASQ (T, U, F, Rely)

66T ScoreBinary
20.96832.65944.3556.041Apr 3, 2026

Evaluation results

MethodLinks
BinaryBase Model=Llama3.1-8B-Inst2026.046603466
BinaryBase Model=Qwen2.5-7B-Inst2026.0460.7039.360.7
KARLBase Model=Llama3.1-8B-Inst2026.0457.732.89.579.7
PromptingBase Model=Llama3.1-8B-Inst2026.0455.80.343.956.1
SFTBase Model=Llama3.1-8B-Inst2026.0453.4046.653.4
SFTBase Model=Qwen2.5-7B-Inst2026.0449.4050.649.4
RLKFBase Model=Llama3.1-8B-Inst2026.0443.327.629.163.3
PromptingBase Model=Qwen2.5-7B-Inst2026.0443.221.83560.2
KARLBase Model=Qwen2.5-7B-Inst2026.044335.221.865.8
Ternary (TruthRL)Base Model=Llama3.1-8B-Inst2026.043957463.5
RLKFBase Model=Qwen2.5-7B-Inst2026.0435.3757.741.8
R-TuningBase Model=Llama3.1-8B-Inst2026.0427.965.66.550.5
Ternary (TruthRL)Base Model=Qwen2.5-7B-Inst2026.0425.267.8747
R-TuningBase Model=Qwen2.5-7B-Inst2026.0422.775.22.141.3