CoChat

LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning

Open access
Lu, Junyi, Yu, Lei, Li, Xiaojia, Yang, Li, Zuo, Chun · 2023 · 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)
Cited by 112

The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.

Abstract

The automation of code review activities, a long-standing pursuit in software engineering, has been primarily addressed by numerous domain-specific pre-trained models. Despite their success, these models frequently demand extensive resources for pre-training from scratch. In contrast, Large Language Models (LLMs) provide an intriguing alternative, given their remarkable capabilities when supplemented with domain-specific knowledge. However, their potential for automating code review tasks remains largely unexplored.In response to this research gap, we present LLaMA-Reviewer, an innovative framework that leverages the capabilities of LLaMA, a popular LLM, in the realm of code review. Mindful of resource constraints, this framework employs parameter-efficient fine-tuning (PEFT) methods, delivering high performance while using less than 1% of trainable parameters.An extensive evaluation of LLaMA-Reviewer is conducted on two diverse, publicly available datasets. Notably, even with the smallest LLaMA base model consisting of 6.7B parameters and a limited number of tuning epochs, LLaMA-Reviewer equals the performance of existing code-review-focused models.The ablation experiments provide insights into the influence of various fine-tuning process components, including input representation, instruction tuning, and different PEFT methods. To foster continuous progress in this field, the code and all PEFT-weight plugins have been made open-source.

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 · 10.1109/issre59848.2023.00026

Cites

26 of 26 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 26 references

Research works printed but not linked: 37

  1. 10.1109/SANER53432.2022.00080 · DOI
  2. 10.1145/3551349.3556955 · DOI · Paper page
  3. 10.1109/ASE51524.2021.9678640 · DOI
  4. 10.1109/SANER56733.2023.00036 · DOI
  5. 10.1145/3540250.3549115 · DOI
  6. 10.1145/3510003.3510213 · DOI
  7. vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 30
  8. 10.1016/j.infsof.2020.106455 · DOI
  9. 10.1145/3377811.3380335 · DOI · Paper page
  10. 10.1145/3468264.3473134 · DOI
  11. 10.1609/aaai.v33i01.33014910 · DOI · Paper page
  12. 10.1016/j.jss.2021.111009 · DOI
  13. 10.1109/ISSRE52982.2021.00056 · DOI
  14. 10.1109/ICSME46990.2020.00054 · DOI
  15. 10.1145/3338906.3340449 · DOI
  16. 10.1007/s10515-020-00275-6 · DOI
  17. 10.1145/3183519.3183525 · DOI · Paper page
  18. 10.1145/2594458 · DOI · Paper page
  19. sülün, 2019, Suggesting reviewers of software artifacts using traceability graphs, Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 1250
  20. 10.1145/3540250.3549104 · DOI
  21. 10.1145/3540250.3549119 · DOI · Paper page
  22. 10.1145/3540250.3549099 · DOI · Paper page
  23. 2023, LLaMA-Reviewer Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning
  24. spadini, 2020, Primers or reminders? the effects of existing review comments on code review, 2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE), 1171
  25. 10.1007/978-3-642-59412-0_35 · doi:10.1007/978-3-642-59412-0_35
  26. 10.1145/3540250.3549098 · DOI · Paper page
  27. 10.1109/ICSE.2019.00021 · DOI · Paper page
  28. 10.1145/3510003.3510621 · DOI · Paper page
  29. chen, 2019, Sequencer: Sequence-to-sequence learning for end-to-end program repair, IEEE Transactions on Software Engineering, 47, 1943
  30. 10.1109/ICSE.2013.6606642 · DOI · Paper page
  31. 10.1145/3510003.3510067 · DOI · Paper page
  32. 10.1145/3540250.3549081 · DOI · Paper page
  33. 10.1109/ICSE43902.2021.00027 · DOI · Paper page
  34. 10.1109/TSE.2022.3158543 · DOI
  35. 10.1109/SANER48275.2020.9054794 · DOI · Paper page
  36. gupta, 2018, Intelligent code reviews using deep learning, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’18) Deep Learning Day
  37. 10.1109/SANER53432.2022.00121 · DOI

Cited by

See all 112

Metadata

Authors
Lu, J., Yu, L., Li, X., Yang, L., & Zuo, C.
Venue
2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)
Publisher
IEEE
Published
2023-10-09
Pages
647-658
OpenAlex
W4388212670
Cited by
112
References
26
FWCI
29.85
Type
conference paper
Language
en
Open access
green
Funders
Science and Technology Service Network Plan

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: LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning. https://app.cochat.ai/papers/10.1109/issre59848.2023.00026
The paper
Lu, J., Yu, L., Li, X., Yang, L., & Zuo, C. (2023). LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning. 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE). https://doi.org/10.1109/issre59848.2023.00026

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.