English

Predicting generalization performance with correctness discriminators

Computation and Language 2025-05-22 v2

Abstract

The ability to predict an NLP model's accuracy on unseen, potentially out-of-distribution data is a prerequisite for trustworthiness. We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for the unseen data. We achieve this by training a discriminator which predicts whether the output of a given sequence-to-sequence model is correct or not. We show across a variety of tagging, parsing, and semantic parsing tasks that the gold accuracy is reliably between the predicted upper and lower bounds, and that these bounds are remarkably close together.

Keywords

Cite

@article{arxiv.2311.09422,
  title  = {Predicting generalization performance with correctness discriminators},
  author = {Yuekun Yao and Alexander Koller},
  journal= {arXiv preprint arXiv:2311.09422},
  year   = {2025}
}

Comments

Appeared in Findings of EMNLP 2024

R2 v1 2026-06-28T13:22:44.390Z