A Close Look into the Calibration of Pre-trained Language Models

by   Yangyi Chen, et al.

Pre-trained language models (PLMs) achieve remarkable performance on many downstream tasks, but may fail in giving reliable estimates of their predictive uncertainty. Given the lack of a comprehensive understanding of PLMs calibration, we take a close look into this new research problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training process? (2) How effective are existing calibration methods? For the first question, we conduct fine-grained control experiments to study the dynamic change in PLMs' calibration performance in training. We consider six factors as control variables, including dataset difficulty, available training samples, training steps, the number of tunable parameters, model scale, and pretraining. In experiments, we observe a consistent change in calibration performance across six factors. We find that PLMs don't learn to become calibrated in training, evidenced by the continual increase in confidence, no matter the predictions are correct or not. We highlight that our finding presents some contradiction with two established conclusions: (a) Larger PLMs are more calibrated; (b) Pretraining improves model calibration. Next, we study the effectiveness of existing calibration methods in mitigating the overconfidence issue, in both in-distribution and various out-of-distribution settings. Besides unlearnable calibration methods, we adapt two recently proposed learnable methods that directly collect data to train models to have reasonable confidence estimations. Also, we propose extended learnable methods based on existing ones to further improve or maintain PLMs calibration without sacrificing the original task performance. Experimental results show that learnable methods significantly reduce PLMs' confidence in wrong predictions, and our methods exhibit superior performance compared with previous methods.


Making Pre-trained Language Models both Task-solvers and Self-calibrators

Pre-trained language models (PLMs) serve as backbones for various real-w...

Can Calibration Improve Sample Prioritization?

Calibration can reduce overconfident predictions of deep neural networks...

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

Large pre-trained language models achieve impressive results across many...

Bag of Tricks for In-Distribution Calibration of Pretrained Transformers

While pre-trained language models (PLMs) have become a de-facto standard...

Teaching Models to Express Their Uncertainty in Words

We show that a GPT-3 model can learn to express uncertainty about its ow...

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

Calibration strengthens the trustworthiness of black-box models by produ...

ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure

Studies have shown that modern neural networks tend to be poorly calibra...

Please sign up or login with your details

Forgot password? Click here to reset