CoChat

BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance

Open access
McCoy, R. Thomas, Min, Junghyun, Linzen, Tal · 2020 · Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Cited by 98

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

If the same neural network architecture is trained multiple times on the same dataset, will it make similar linguistic generalizations across runs?To study this question, we finetuned 100 instances of BERT on the Multigenre Natural Language Inference (MNLI) dataset and evaluated them on the HANS dataset, which evaluates syntactic generalization in natural language inference.On the MNLI development set, the behavior of all instances was remarkably consistent, with accuracy ranging between 83.6% and 84.8%.In stark contrast, the same models varied widely in their generalization performance.For example, on the simple case of subject-object swap (e.g., determining that the doctor visited the lawyer does not entail the lawyer visited the doctor), accuracy ranged from 0.0% to 66.2%.Such variation is likely due to the presence of many local minima in the loss surface that are equally attractive to a low-bias learner such as a neural network; decreasing the variability may therefore require models with stronger inductive biases.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2020.blackboxnlp-1.21

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 15 references

Cited by

See all 98

Metadata

Authors
McCoy, R. T., Min, J., & Linzen, T.
Venue
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Published
2020
Pages
217-227
OpenAlex
W3099624838
Cited by
98
References
15
FWCI
8.26
Type
conference paper
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance. https://app.cochat.ai/papers/10.18653/v1/2020.blackboxnlp-1.21
The paper
McCoy, R. T., Min, J., & Linzen, T. (2020). BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance. Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. https://doi.org/10.18653/v1/2020.blackboxnlp-1.21

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.