Training language models to follow instructions with human feedback
Open paper
Benchmark
Model
Rank
Results
question-answering-on-tiq
InstructGpt
#5
P@1: 23.6
question-answering-on-timequestions
InstructGPT
#8
P@1: 22.4
sentence-completion-on-hellaswag
InstructGPT 175B (few-shot)
#60
Accuracy: 82.0
Rank counts only results with a code link.