CoChat

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

Open access
Li, Shaobo, Li, Xiaoguang, Shang, Lifeng, Dong, Zhenhua, Sun, Chengjie, Liu, Bingquan, Ji, Zhenzhou, Jiang, Xin, Liu, Qun · 2022 · Findings of the Association for Computational Linguistics: ACL 2022
Cited by 30

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

Abstract

Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs).Many works show the PLMs' ability to fill in the missing factual words in cloze-style prompts such as "Dante was born in [MASK]."However, it is still a mystery how PLMs generate the results correctly: relying on effective clues or shortcut patterns?We try to answer this question by a causal-inspired analysis that quantitatively measures and evaluates the wordlevel patterns that PLMs depend on to generate the missing words.We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred.Our analysis shows: (1) PLMs generate the missing factual words more by the positionally close and highly co-occurred words than the knowledge-dependent words; (2) the dependence on the knowledge-dependent words is more effective than the positionally close and highly co-occurred words.Accordingly, we conclude that the PLMs capture the factual knowledge ineffectively because of depending on the inadequate associations.

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-acl.136

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 30

Metadata

Authors
Li, S., Li, X., Shang, L., Dong, Z., Sun, C., Liu, B., Ji, Z., Jiang, X., & Liu, Q.
Venue
Findings of the Association for Computational Linguistics: ACL 2022
Published
2022
Pages
1720-1732
OpenAlex
W4226455589
Cited by
30
References
15
FWCI
4.34
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: How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis. https://app.cochat.ai/papers/10.18653/v1/2022.findings-acl.136
The paper
Li, S., Li, X., Shang, L., Dong, Z., Sun, C., Liu, B., Ji, Z., Jiang, X., & Liu, Q. (2022). How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis. Findings of the Association for Computational Linguistics: ACL 2022. https://doi.org/10.18653/v1/2022.findings-acl.136

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.