CoChat

Probing Across Time: What Does RoBERTa Know and When?

Open access
Liu, Zeyu, Wang, Yizhong, Kasai, Jungo, Hajishirzi, Hannaneh, Smith, Noah A. · 2021 · Findings of the Association for Computational Linguistics: EMNLP 2021
Cited by 35

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Models of language trained on very large corpora have been demonstrated useful for natural language processing.As fixed artifacts, they have become the object of intense study, with many researchers "probing" the extent to which they acquire and readily demonstrate linguistic abstractions, factual and commonsense knowledge, and reasoning abilities.Recent work applied several probes to intermediate training stages to observe the developmental process of a large-scale model (Chiang et al., 2020).Following this effort, we systematically answer a question: for various types of knowledge a language model learns, when during (pre)training are they acquired?Using RoBERTa as a case study, we find: linguistic knowledge is acquired fast, stably, and robustly across domains.Facts and commonsense are slower and more domainsensitive.Reasoning abilities are, in general, not stably acquired.As new datasets, pretraining protocols, and probes emerge, we believe that probing-across-time analyses can help researchers understand the complex, intermingled learning that these models undergo and guide us toward more efficient approaches that accomplish necessary learning faster.

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.findings-emnlp.71

Cites

13 of 13 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 13 references

Cited by

See all 35

Metadata

Authors
Liu, Z., Wang, Y., Kasai, J., Hajishirzi, H., & Smith, N. A.
Venue
Findings of the Association for Computational Linguistics: EMNLP 2021
Published
2021
Pages
820-842
OpenAlex
W3213280751
Cited by
35
References
13
FWCI
3.33
Type
conference paper
Language
en
Open access
gold

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: Probing Across Time: What Does RoBERTa Know and When? https://app.cochat.ai/papers/10.18653/v1/2021.findings-emnlp.71
The paper
Liu, Z., Wang, Y., Kasai, J., Hajishirzi, H., & Smith, N. A. (2021). Probing Across Time: What Does RoBERTa Know and When? Findings of the Association for Computational Linguistics: EMNLP 2021. https://doi.org/10.18653/v1/2021.findings-emnlp.71

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.