Hello,
Thank you for your work and sharing the evaluation results on the Libra-Test dataset.
I was wondering if you have also conducted any evaluations on OOD datasets? For example, have you tested the model's generalization capability on benchmarks used by ShieldLM? Do these results demonstrate the superiority of Libra-Guard?
Hello,
Thank you for your work and sharing the evaluation results on the Libra-Test dataset.
I was wondering if you have also conducted any evaluations on OOD datasets? For example, have you tested the model's generalization capability on benchmarks used by ShieldLM? Do these results demonstrate the superiority of Libra-Guard?