List your company

Truthfulness Detection on True-False dataset

71.47AnimalsPRISM-SAPLMA
45.251652.058358.86565.6717Nov 7, 2024

Evaluation results

MethodLinks
PRISM-SAPLMALLM=LLaMA2-7B-Chat2024.1171.4789.3682.7967.0575.3978.0477.35
PRISM-MMLLM=LLaMA2-7B-Chat2024.1170.0490.679.0863.8570.3177.5675.24
SAPLMALLM=LLaMA2-7B-Chat2024.1165.396762.6260.5775.8562.3365.63
EUBHDLLM=LLaMA2-7B-Chat2024.1156.8361.9759.6360.0455.6355.9158.34
LN-PPLLM=LLaMA2-7B-Chat2024.1154.9656.5353.5757.2759.4855.2756.18
MMLLM=LLaMA2-7B-Chat2024.115356.8856.4855.8161.3750.7555.72
MINDLLM=LLaMA2-7B-Chat2024.1146.2646.6449.9748.550.2550.2348.64