Skip to content

Latest commit

 

History

History
31 lines (19 loc) · 473 Bytes

README.md

File metadata and controls

31 lines (19 loc) · 473 Bytes

CME-EMNLP2022

Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates, EMNLP 2022

Code and datasets for our paper.

Instructions

Use the following instructions to set up the dependencies:

$ conda activate [your_anaconda3_environment]
$ pip install -r requirements.txt

Datasets

Place it in the root directory.

Training

bash example.sh

Evaluating Calibration

bash eval.sh