English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Calibration strengthens the trustworthiness of black-box models by producingbetter accurate confidence estimates on given examples. However, little isknown about if model explanations can help confidence calibration. Intuitively,humans look at important features attributions and decide whether the model istrustworthy. Similarly, the explanations can tell us when the model may or maynot know. Inspired by this, we propose a method named CME that leverages modelexplanations to make the model less confident with non-inductive attributions.The idea is that when the model is not highly confident, it is difficult toidentify strong indications of any class, and the tokens accordingly do nothave high attribution scores for any class and vice versa. We conduct extensiveexperiments on six datasets with two popular pre-trained language models in thein-domain and out-of-domain settings. The results show that CME improvescalibration performance in all settings. The expected calibration errors arefurther reduced when combined with temperature scaling. Our findings highlightthat model explanations can help calibrate posterior estimates.

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