CoChat

FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Open access
Guo, Han, Rajani, Nazneen, Hase, Peter, Bansal, Mohit, Xiong, Caiming · 2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Cited by 55

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Abstract

Influence functions approximate the "influences" of training data-points for test predictions and have a wide variety of applications.Despite the popularity, their computational cost does not scale well with model and training data size.We present FASTIF, a set of simple modifications to influence functions that significantly improves their run-time.We use k-Nearest Neighbors (kNN) to narrow the search space down to a subset of good candidate data points, identify the configurations that best balance the speed-quality trade-off in estimating the inverse Hessian-vector product, and introduce a fast parallel variant.Our proposed method achieves about 80X speedup while being highly correlated with the original influence values.With the availability of the fast influence functions, we demonstrate their usefulness in four applications.First, we examine whether influential data-points can "explain" test time behavior using the framework of simulatability.Second, we visualize the influence interactions between training and test data-points.Third, we show that we can correct model errors by additional fine-tuning on certain influential data-points, improving the accuracy of a trained MultiNLI model by 2.5% on the HANS dataset.Finally, we experiment with a similar setup but fine-tuning on datapoints not seen during training, improving the model accuracy by 2.8% and 1.7% on HANS and ANLI datasets respectively.Overall, our fast influence functions can be efficiently applied to large models and datasets, and our experiments demonstrate the potential of influence functions in model interpretation and correcting model errors. 1

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/v1/2021.emnlp-main.808

Cites

30 of 30 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 30 references

Cited by

See all 55

Metadata

Authors
Guo, H., Rajani, N., Hase, P., Bansal, M., & Xiong, C.
Venue
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Published
2021
Pages
10333-10350
OpenAlex
W3118560954
Cited by
55
References
30
FWCI
4.57
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: FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.808
The paper
Guo, H., Rajani, N., Hase, P., Bansal, M., & Xiong, C. (2021). FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.808

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.