CoChat

CERT: Continual Pre-training on Sketches for Library-oriented Code Generation

Open access
Zan, Daoguang, Chen, Bei, Yang, Dejian, Lin, Zeqi, Kim, Minsu, Guan, Bei, Wang, Yongji, Chen, Weizhu, Lou, Jian-Guang · 2022 · Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Cited by 65

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

Abstract

Code generation is a longstanding challenge, aiming to generate a code snippet based on a natural language description. Usually, expensive text-code paired data is essential for training a code generation model. Recently, thanks to the success of pre-training techniques, large language models are trained on large unlabelled code corpora and perform well in generating code. In this paper, we investigate how to leverage an unlabelled code corpus to train a model for library-oriented code generation. Since it is a common practice for programmers to reuse third-party libraries, in which case the text-code paired data are harder to obtain due to the huge number of libraries. We observe that library-oriented code snippets are more likely to share similar code sketches. Hence, we present CERT with two steps: a sketcher generates the sketch, then a generator fills the details in the sketch. Both the sketcher and generator are continually pre-trained upon a base model using unlabelled data. Also, we carefully craft two benchmarks to evaluate library-oriented code generation named PandasEval and NumpyEval. Experimental results have shown the impressive performance of CERT. For example, it surpasses the base model by an absolute 15.67% improvement in terms of pass@1 on PandasEval. Our work is available at https://github.com/microsoft/PyCodeGPT.

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 · 10.24963/ijcai.2022/329

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 65

Metadata

Authors
Zan, D., Chen, B., Yang, D., Lin, Z., Kim, M., Guan, B., Wang, Y., Chen, W., & Lou, J.-G.
Venue
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Published
2022-07
Pages
2369-2375
OpenAlex
W4285600327
Cited by
65
References
13
FWCI
13.27
Type
conference paper
Language
en
Open access
bronze

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: CERT: Continual Pre-training on Sketches for Library-oriented Code Generation. https://app.cochat.ai/papers/10.24963/ijcai.2022/329
The paper
Zan, D., Chen, B., Yang, D., Lin, Z., Kim, M., Guan, B., Wang, Y., Chen, W., & Lou, J.-G. (2022). CERT: Continual Pre-training on Sketches for Library-oriented Code Generation. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. https://doi.org/10.24963/ijcai.2022/329

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.