|
We employ the original [Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) model, which we further fine-tune using carefully selected samples from our compiled dataset (available at https://github.com/rhyang2021/LoGU). This refined model is subsequently utilized within our LoGU task, specifically targeting the challenges of **uncertainty-suppression** and **uncertainty-misalignment**. For additional details, please refer to our [Github](https://github.com/rhyang2021/LoGU) and [Paper](https://arxiv.org/abs/2410.14309). |
