SelfInst
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SelfInst
21.7Rouge-L
73
SelfInst
23.4R-L Score
50
SelfInst
21.31ROUGE-L
21
SelfInst (OOD)
23.2Rouge-L
20
SelfInst Out-of-Distribution
51.6GPT-4o Score
17
SelfInst
11.31Rouge-L
16
SelfInst (test)
60.16LLM-as-a-Judge Score
2