English

How Reliable are Model Diagnostics?

Computation and Language 2022-02-01 v1 Machine Learning

Abstract

In the pursuit of a deeper understanding of a model's behaviour, there is recent impetus for developing suites of probes aimed at diagnosing models beyond simple metrics like accuracy or BLEU. This paper takes a step back and asks an important and timely question: how reliable are these diagnostics in providing insight into models and training setups? We critically examine three recent diagnostic tests for pre-trained language models, and find that likelihood-based and representation-based model diagnostics are not yet as reliable as previously assumed. Based on our empirical findings, we also formulate recommendations for practitioners and researchers.

Keywords

Cite

@article{arxiv.2105.05641,
  title  = {How Reliable are Model Diagnostics?},
  author = {Vamsi Aribandi and Yi Tay and Donald Metzler},
  journal= {arXiv preprint arXiv:2105.05641},
  year   = {2022}
}

Comments

ACL 2021 Findings

R2 v1 2026-06-24T02:02:14.832Z