CoChat

Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions

Open access
Han, Xiaochuang, Wallace, Byron C., Tsvetkov, Yulia · 2020 · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Cited by 104

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

Modern deep learning models for NLP are notoriously opaque.This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention weights.Such approaches aim to provide explanations for a particular model prediction by highlighting important words in the corresponding input text.While this might be useful for tasks where decisions are explicitly influenced by individual tokens in the input, we suspect that such highlighting is not always suitable for tasks where model decisions should be driven by more complex reasoning.In this work, we investigate the use of influence functions for NLP, providing an alternative approach to interpreting neural text classifiers.Influence functions explain the decisions of a model by identifying influential training examples.Despite the promise of this approach, influence functions have not yet been extensively evaluated in the context of NLP, a gap addressed by this work.We conduct a comparison between influence functions and common word-saliency methods on representative tasks.As suspected, we find that influence functions are particularly useful for natural language inference, a task in which 'saliency maps' may not provide clear interpretation.Furthermore, we develop a new quantitative measure based on influence functions that can reveal artifacts in training data.

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.492

Cites

19 of 19 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 19 references

Cited by

See all 104

Metadata

Authors
Han, X., Wallace, B. C., & Tsvetkov, Y.
Venue
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Published
2020
Pages
5553-5563
OpenAlex
W3034475796
Cited by
104
References
19
FWCI
8.57
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: Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions. https://app.cochat.ai/papers/10.18653/v1/2020.acl-main.492
The paper
Han, X., Wallace, B. C., & Tsvetkov, Y. (2020). Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.492

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.