Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?

Urja Khurana, Eric Nalisnick, Antske Fokkens, Swabha Swayamdipta

Research Area: Evaluation, Societal implications

Keywords: calibration, human subjectivity, disagreement, hate speech detection

TL;DR: We propose Crowd-Calibrator, a soft calibration method, where we calibrate models for subjective tasks according to whether their prediction is close to what the crowd thinks.

Abstract: Subjective tasks in NLP have been mostly relegated to objective standards, where the gold label is decided by taking the majority vote. This obfuscates annotator disagreement and the inherent uncertainty of the label. We argue that subjectivity should factor into model decisions and play a direct role via calibration under a selective prediction setting. Specifically, instead of calibrating confidence purely from the model’s perspective, we calibrate models for subjective tasks based on crowd worker agreement. Our method, Crowd-Calibrator, models the distance between the distribution of crowd worker labels and the model’s own distribution over labels to inform whether the model should abstain from a decision. On two highly subjective tasks, hate speech detection and natural language inference, our experiments show Crowd-Calibrator either outperforms or achieves competitive performance with existing selective prediction baselines. Our findings highlight the value of bringing human decision-making into model predictions.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 768