List your company

Instruction Following on X-AlpacaEval

70.9Chinese Win RatePLUG
44.48451.34258.265.058Nov 15, 2023

Evaluation results

MethodLinks
PLUGFoundation LLM=LLaMA-2-13B, Comparison Baseline=Pivot-Only2023.1170.919.151.876.512.763.967.617.849.86420.943.1
PLUGFoundation LLM=LLaMA-2-13B, Comparison Baseline=Mono. Response2023.115825.232.864.119.944.250.325.824.55327.625.5
PLUGFoundation LLM=PolyLM-13B, Comparison Baseline=Pivot-Only2023.1153.232.320.979.911.168.865.718.547.257.424.133.3
PLUGFoundation LLM=LLaMA-2-13B, Comparison Baseline=Mono. + Translation2023.11532825.162.720.142.650.126.623.551.325.625.7
PLUGFoundation LLM=PolyLM-Instruct-13B, Comparison Baseline=Pivot-Only2023.1152.831.920.977.112.964.26220.141.956.726.330.4
PLUGFoundation LLM=LLaMA-2-13B, Comparison Baseline=Mono. + Code-Switch2023.1150.231.618.655.225.629.646.230.915.348.429.918.5
PLUGFoundation LLM=PolyLM-Instruct-13B, Comparison Baseline=Mono. Response2023.1148.532.116.464.51945.554.222.931.344.832.112.7
PLUGFoundation LLM=PolyLM-13B, Comparison Baseline=Mono. + Translation2023.114734.312.767.320.946.551.927.524.550.231.219
PLUGFoundation LLM=PolyLM-13B, Comparison Baseline=Mono. + Code-Switch2023.114737.811.257.525.132.448.829.419.445.83411.8
PLUGFoundation LLM=PolyLM-Instruct-13B, Comparison Baseline=Mono. + Translation2023.1146.833.513.36521.843.351.12922.148.332.615.7
PLUGFoundation LLM=PolyLM-Instruct-13B, Comparison Baseline=Mono. + Code-Switch2023.1146.132.813.357.823.933.949.629.819.845.532.912.5
PLUGFoundation LLM=PolyLM-13B, Comparison Baseline=Mono. Response2023.1145.534.510.967.318.448.959.322.137.144.530.713.8