A Survey on Out-of-Distribution Evaluation of Neural NLP Models

Xinzhe Li, Ming Liu, Shang Gao, Wray Buntine
6/27/2023
cs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Models Out of Line: A Fourier Lens on Distribution Shift Robustness

86% match2022

Mixture Data for Training Cannot Ensure Out-of-distribution Generalization

86% match2023

Out-of-Distribution Generalization in Text Classification: Past, Present, and Future

83% match2023

Assaying Out-Of-Distribution Generalization in Transfer Learning

83% match1 repo92022

In Search of Forgotten Domain Generalization

82% match1 repo12024

Label Augmentation for Neural Networks Robustness

82% match2024

Cite this paper

@article{li2023survey,
  title  = {A Survey on Out-of-Distribution Evaluation of Neural NLP Models},
  author = {Xinzhe Li and Ming Liu and Shang Gao and Wray Buntine},
  year   = {2023},
  eprint = {2306.15261},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.15261v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.15261.svg)](https://codeofpaper.com/paper/2306.15261)

Discussion