Calibrating Factual Knowledge in Pretrained Language Models
This work addresses the issue of factual inaccuracies in PLMs for users relying on them for knowledge-intensive tasks, representing an incremental improvement over existing calibration methods.
The authors tackled the problem of incorrect factual knowledge stored in pretrained language models by proposing CaliNet, a lightweight method to calibrate facts without retraining, which improved performance on knowledge probing tasks and demonstrated knowledge generalization in closed-book question answering.
Previous literature has proved that Pretrained Language Models (PLMs) can store factual knowledge. However, we find that facts stored in the PLMs are not always correct. It motivates us to explore a fundamental question: How do we calibrate factual knowledge in PLMs without re-training from scratch? In this work, we propose a simple and lightweight method CaliNet to achieve this goal. To be specific, we first detect whether PLMs can learn the right facts via a contrastive score between right and fake facts. If not, we then use a lightweight method to add and adapt new parameters to specific factual texts. Experiments on the knowledge probing task show the calibration effectiveness and efficiency. In addition, through closed-book question answering, we find that the calibrated PLM possesses knowledge generalization ability after fine-tuning. Beyond the calibration performance, we further investigate and visualize the knowledge calibration mechanism.