ResearchBenchmarksText Classification on Trustworthiness Plain-text OODFollow68.44AccuracyChatGLM235.326443.923252.5261.1168Feb 20, 2024Evaluation ResultsMethodMethodLinksAccuracyChatGLM2Setting=Zero-shotSetting=Zero-shot2024.0268.44Llama2Setting=Zero-shotSetting=Zero-shot2024.0259.21SoMeLVLMSetting=Zero-shotSetting=Zero-shot2024.0243.52VicunaSetting=Zero-shotSetting=Zero-shot2024.0236.6