Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.

Unit Testing for Concepts in Neural Networks

Open access
Lovering, Charles, Pavlick, Ellie · 2022 · Transactions of the Association for Computational Linguistics

Abstract

Many complex problems are naturally understood in terms of symbolic concepts. For example, our concept of “cat” is related to our concepts of “ears” and “whiskers” in a non-arbitrary way. Fodor (1998) proposes one theory of concepts, which emphasizes symbolic representations related via constituency structures. Whether neural networks are consistent with such a theory is open for debate. We propose unit tests for evaluating whether a system’s behavior is consistent with several key aspects of Fodor’s criteria. Using a simple visual concept learning task, we evaluate several modern neural architectures against this specification. We find that models succeed on tests of groundedness, modularity, and reusability of concepts, but that important questions about causality remain open. Resolving these will require new methods for analyzing models’ internal states.

Overview

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00514

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 40 references

Research works printed but not linked: 21

  1. Adebayo, 2020, Debugging tests for model explanations, arXiv preprint arXiv:2011.05429 · arXiv
  2. Adi, 2017, Fine- grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
  3. Andreas, 2019, Measuring compositionality in representation learning
  4. Andreas, 2016, Neural module networks, 39
  5. Carey, 2009, The Origin of Concepts, 10.1093/acprof:oso/9780195367638.001.0001 · DOI · Paper page
  6. Chang, 2018, Explaining image classifiers by counterfactual generation, arXiv preprint arXiv:1807.08024 · arXiv
  7. Dosovitskiy, 2020, An image is worth 16 × 16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929 · arXiv
  8. Goyal, 2019, Explaining classifiers with causal concept effect, arXiv preprint arXiv:1907. 07165
  9. Goyal, 2019, Counterfactual visual explanations, 2376
  10. He, 2016, Deep residual learning for image recognition, 770
  11. Hupkes, 2018, Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure, Journal of Artificial Intelligence Research, 61, 907, 10.1613/jair.1.11196 · DOI · Paper page
  12. Ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 448
  13. Jackman, 2020, Meaning Holism
  14. Lake, 2018, Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks
  15. Lovering, 2020, Predicting inductive biases of pre-trained models
  16. Meng, 2022, Locating and editing factual knowledge in GPT, arXiv preprint arXiv:2202.05262 · arXiv
  17. Radford, 2021, Learning transferable visual models from natural language supervision, 8748, 10.48550/arXiv.2103.00020 · DOI · Paper page
  18. Sermanet, 2013, Overfeat: Integrated recognition, localization and detection using convolutional networks, arXiv preprint arXiv:1312.6229 · arXiv
  19. Sundararajan, 2017, Axiomatic attribution for deep networks, 3319
  20. Tenney, 2019, What do you learn from context? Probing for sentence structure in contextualized word representations
  21. Veldhoen, 2016, Diagnostic classifiers: Revealing how neural networks process hierarchical structure

Cited by

See all 12

Metadata

Authors
Lovering, C., & Pavlick, E.
Affiliations
Brown University (US)
Corresponding author
  • Lovering, Charles
  • Pavlick, Ellie
Venue
Transactions of the Association for Computational Linguistics
Publisher
MIT Press
Published
2022
Volume
10
Pages
1193-1208
ISSN
2307-387X (ISSN-L)
OpenAlex
W4313119036
Cited by
12
References
40
Citations by year
2025: 2 · 2024: 4 · 2023: 4 · 2022: 2
FWCI
2.76
Type
journal article
Language
en
Open access
Locations
  • Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • Brown University
  • Defense Advanced Research Projects Agency
Topics
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
  • Social Sciences › Arts and Humanities › Philosophy › Philosophy and Theoretical Science
Keywords
unit testing, artificial neural networks, symbolic concepts, visual concept learning, groundedness, modularity, causality

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: Unit Testing for Concepts in Neural Networks. https://app.cochat.ai/papers/10.1162/tacl_a_00514
The paper
Lovering, C., & Pavlick, E. (2022). Unit Testing for Concepts in Neural Networks. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00514

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.