Towards Improving Selective Prediction Ability of NLP Systems

TL;DR

This paper introduces a calibration-based method to enhance the selective prediction ability of NLP systems, especially in out-of-domain scenarios, by improving confidence estimates for more reliable decision-making.

Contribution

The authors propose a novel calibration approach using confidence and difficulty scores, improving selective prediction in NLP tasks over existing methods.

Findings

Significant improvement in out-of-domain prediction accuracy.

Enhanced calibration leads to better selective prediction performance.

Method outperforms baseline on NLI and Duplicate Detection tasks.

Abstract

It's better to say "I can't answer" than to answer incorrectly. This selective prediction ability is crucial for NLP systems to be reliably deployed in real-world applications. Prior work has shown that existing selective prediction techniques fail to perform well, especially in the out-of-domain setting. In this work, we propose a method that improves probability estimates of models by calibrating them using prediction confidence and difficulty score of instances. Using these two signals, we first annotate held-out instances and then train a calibrator to predict the likelihood of correctness of the model's prediction. We instantiate our method with Natural Language Inference (NLI) and Duplicate Detection (DD) tasks and evaluate it in both In-Domain (IID) and Out-of-Domain (OOD) settings. In (IID, OOD) settings, we show that the representations learned by our calibrator result in an improvement of (15.81%, 5.64%) and (6.19%, 13.9%) over 'MaxProb' -- a selective prediction baseline -- on NLI and DD tasks respectively.