CoChat

Obtaining Faithful Interpretations from Compositional Neural Networks

Open access
Subramanian, Sanjay, Bogin, Ben, Gupta, Nitish, Wolfson, Tomer, Singh, Sameer, Berant, Jonathan, Gardner, Matt · 2020 · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Cited by 37

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

Abstract

Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture.However, prior work implicitly assumed that the structure of the network modules, describing the abstract reasoning process, provides a faithful explanation of the model's reasoning; that is, that all modules perform their intended behaviour.In this work, we propose and conduct a systematic evaluation of the intermediate outputs of NMNs on NLVR2 and DROP, two datasets which require composing multiple reasoning steps.We find that the intermediate outputs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour.To remedy that, we train the model with auxiliary supervision and propose particular choices for module architecture that yield much better faithfulness, at a minimal cost to accuracy.

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.acl-main.495

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 37

Metadata

Authors
Subramanian, S., Bogin, B., Gupta, N., Wolfson, T., Singh, S., Berant, J., & Gardner, M.
Venue
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Published
2020
Pages
5594-5608
OpenAlex
W3023935934
Cited by
37
References
15
FWCI
3.53
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: Obtaining Faithful Interpretations from Compositional Neural Networks. https://app.cochat.ai/papers/10.18653/v1/2020.acl-main.495
The paper
Subramanian, S., Bogin, B., Gupta, N., Wolfson, T., Singh, S., Berant, J., & Gardner, M. (2020). Obtaining Faithful Interpretations from Compositional Neural Networks. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.495

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.