Instruction Following

5 benchmarks1135 papers

Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.

Benchmarks

Instruction Following on LLaVA-Bench

avg score

Instruction Following on IFEval

Inst-level loose-accuracyInst-level strict-accuracyPrompt-level loose-accuracyPrompt-level strict-accuracy