Fast Few-shot Debugging for NLU Test Suites

Christopher Malon, Kai Li, Erik Kruus

Abstract

We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem. Given a few debugging examples of a certain phenomenon, and a held-out test set of the same phenomenon, we aim to maximize accuracy on the phenomenon at a minimal cost of accuracy on the original test set. We examine several methods that are faster than full epoch retraining. We introduce a new fast method, which samples a few in-danger examples from the original training set. Compared to fast methods using parameter distance constraints or Kullback-Leibler divergence, we achieve superior original accuracy for comparable debugging accuracy.
BibTeX
@inproceedings{malon2022fast,
  author = {Christopher Malon and Kai Li and Erik Kruus},
  title = {{Fast Few-shot Debugging for NLU Test Suites}},
  booktitle = {DeeLIO @ ACL},
  year = {2022},
  doi = {10.18653/v1/2022.deelio-1.8},
}

Loading related content...

Figure