List your company

Online Out-of-Distribution Detection on GSM8K Near-shift OOD

93.39AccuracyTV Score
74.597279.476184.35589.2339May 22, 2024

Evaluation results

MethodLinks
TV ScoreModel=Llama2-7B, Evaluation Scenario=Online Detection2024.0593.392.05
Input EmbeddingModel=Llama2-7B, Evaluation Scenario=Online Detection2024.0581.4910.08
Output EmbeddingModel=Llama2-7B, Evaluation Scenario=Online Detection2024.0575.323.36