CoChat

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm

Open access
Xu, Lei, Chen, Yangyi, Cui, Ganqu, Gao, Hongcheng, Liu, Zhiyuan · 2022 · Findings of the Association for Computational Linguistics: NAACL 2022
Cited by 45

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

Abstract

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.However, we find that this learning paradigm inherits the vulnerability from the pre-training stage, where model predictions can be misled by inserting certain triggers into the text.In this paper, we explore this universal vulnerability by either injecting backdoor triggers or searching for adversarial triggers on pre-trained language models using only plain text.In both scenarios, we demonstrate that our triggers can totally control or severely decrease the performance of prompt-based models fine-tuned on arbitrary downstream tasks, reflecting the universal vulnerability of the prompt-based learning paradigm.Further experiments show that adversarial triggers have good transferability among language models.We also find conventional fine-tuning models are not vulnerable to adversarial triggers constructed from pre-trained language models.We conclude by proposing a potential solution to mitigate our attack methods.Code and data are publicly available.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/v1/2022.findings-naacl.137

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 45

Metadata

Authors
Xu, L., Chen, Y., Cui, G., Gao, H., & Liu, Z.
Venue
Findings of the Association for Computational Linguistics: NAACL 2022
Published
2022
Pages
1799-1810
OpenAlex
W4224903411
Cited by
45
References
15
FWCI
6.14
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: Exploring the Universal Vulnerability of Prompt-based Learning Paradigm. https://app.cochat.ai/papers/10.18653/v1/2022.findings-naacl.137
The paper
Xu, L., Chen, Y., Cui, G., Gao, H., & Liu, Z. (2022). Exploring the Universal Vulnerability of Prompt-based Learning Paradigm. Findings of the Association for Computational Linguistics: NAACL 2022. https://doi.org/10.18653/v1/2022.findings-naacl.137

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.