2022

Explainable AI for Pre-Trained Code Models: What Do They Learn? When They Do Not Work?

Mohammadkhani, Ahmad Haji, Tantithamthavorn, Chakkrit, Hemmati, Hadi

Understand

In recent years, there has been a wide interest in designing deep neural network-based models that automate downstream software engineering tasks on source code, such as code document generation, code search, and program repair.

Although the main objective of these studies is to improve the effectiveness of the downstream task, many studies only attempt to employ the next best neural network model, without a proper in-depth analysis of why a particular solution works or does not, on particular tasks or scenarios.
In this paper, using an example eXplainable AI (XAI) method (attention mechanism), we study two recent large language models (LLMs) for code (CodeBERT and GraphCodeBERT) on a set of software engineering downstream tasks: code document generation (CDG), code refinement (CR), and code translation (CT).
Through quantitative and qualitative studies, we identify what CodeBERT and GraphCodeBERT learn (put the highest attention on, in terms of source code token types), on these tasks.

Built on

K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics , 2002, pp. 311–318
2002
Earlier work this paper cites.
E. Loper and S. Bird, “Nltk: The natural language toolkit,” CoRR , vol. cs.CL/0205028, 2002. [Online]. Available: http://dblp.uni-trier.de/db/journals/corr/corr0205.html#cs-CL-0205028
2002
Earlier work this paper cites.
C.-Y. Lin and F. J. Och, “Orange: a method for evaluating automatic evaluation metrics for machine translation,” in COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics , 2004, pp. 501–507
2004
Earlier work this paper cites.
T. Nguyen, P. C. Rigby, A. T. Nguyen, M. Karanfil, and T. N. Nguyen, “T2api: Synthesizing api code usage templates from english texts with statistical translation,” in Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering , 2016, pp. 1013–1017
2016
Earlier work this paper cites.
S. Jiang, A. Armaly, and C. McMillan, “Automatically generating commit messages from diffs using neural machine translation,” in 2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE) . IEEE, 2017, pp. 135–146
2017
Earlier work this paper cites.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805 , 2018
Original
2018
Earlier work this paper cites.
X. Gu, H. Zhang, and S. Kim, “Deep code search,” in 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE) . IEEE, 2018, pp. 933–944
2018
Earlier work this paper cites.
L. Liu, X. Hu, W. Song, R. Fu, T. Liu, and G. Hu, “Neural multitask learning for simile recognition,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , 2018, pp. 1543–1553
2018
Earlier work this paper cites.
X. Hu, G. Li, X. Xia, D. Lo, and Z. Jin, “Deep code comment generation,” in 2018 IEEE/ACM 26th International Conference on Program Comprehension (ICPC) . IEEE, 2018, pp. 200–20 010
2018
Earlier work this paper cites.
J. Humphreys and H. K. Dam, “An explainable deep model for defect prediction,” in 2019 IEEE/ACM 7th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE) . IEEE, 2019, pp. 49–55
2019
Earlier work this paper cites.
Z. Chen, S. Kommrusch, M. Tufano, L.-N. Pouchet, D. Poshyvanyk, and M. Monperrus, “Sequencer: Sequence-to-sequence learning for end-to-end program repair,” IEEE Transactions on Software Engineering , vol. 47, no. 9, pp. 1943–1959, 2019
2019
Earlier work this paper cites.
A. LeClair, S. Haque, L. Wu, and C. McMillan, “Improved code summarization via a graph neural network,” in Proceedings of the 28th international conference on program comprehension , 2020, pp. 184–195
2020
Earlier work this paper cites.

Similar

Z. Feng, D. Guo, D. Tang, N. Duan, X. Feng, M. Gong, L. Shou, B. Qin, T. Liu, D. Jiang et al. , “Codebert: A pre-trained model for programming and natural languages,” in Findings of the Association for Computational Linguistics: EMNLP 2020 , 2020, pp. 1536–1547
2020
Cited alongside, same era.
D. Guo, S. Ren, S. Lu, Z. Feng, D. Tang, S. Liu, L. Zhou, N. Duan, A. Svyatkovskiy, S. Fu et al. , “Graphcodebert: Pre-training code representations with data flow,” arXiv preprint arXiv:2009.08366 , 2020
Original
2020
Cited alongside, same era.
J. Jiarpakdee, C. K. Tantithamthavorn, H. K. Dam, and J. Grundy, “An empirical study of model-agnostic techniques for defect prediction models,” IEEE Transactions on Software Engineering , vol. 48, no. 1, pp. 166–185, 2020
2020
Cited alongside, same era.
S. Wattanakriengkrai, P. Thongtanunam, C. Tantithamthavorn, H. Hata, and K. Matsumoto, “Predicting defective lines using a model-agnostic technique,” IEEE Transactions on Software Engineering , vol. 48, no. 5, pp. 1480–1496, 2020
2020
Cited alongside, same era.
C. Khanan, W. Luewichana, K. Pruktharathikoon, J. Jiarpakdee, C. Tantithamthavorn, M. Choetkiertikul, C. Ragkhitwetsagul, and T. Sunetnanta, “Jitbot: An explainable just-in-time defect prediction bot,” in 2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE) . IEEE, 2020, pp. 1336–1339
2020
Cited alongside, same era.
S. Haque, A. LeClair, L. Wu, and C. McMillan, “Improved automatic summarization of subroutines via attention to file context,” in Proceedings of the 17th International Conference on Mining Software Repositories , 2020, pp. 300–310
2020
Cited alongside, same era.
Y. Li, S. Wang, and T. N. Nguyen, “Dlfix: Context-based code transformation learning for automated program repair,” in Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering , 2020, pp. 602–614
2020
Cited alongside, same era.
B. Roziere, M.-A. Lachaux, L. Chanussot, and G. Lample, “Unsupervised translation of programming languages,” Advances in Neural Information Processing Systems , vol. 33, pp. 20 601–20 611, 2020
2020
Cited alongside, same era.
A. Svyatkovskiy, S. K. Deng, S. Fu, and N. Sundaresan, “Intellicode compose: Code generation using transformer,” in Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering , 2020, pp. 1433–1443
2020
Cited alongside, same era.
G. Shobha, A. Rana, V. Kansal, and S. Tanwar, “Code clone detection—a systematic review,” Emerging Technologies in Data Mining and Information Security , pp. 645–655, 2021
2021
Cited alongside, same era.
C. Pornprasit, C. Tantithamthavorn, J. Jiarpakdee, M. Fu, and P. Thongtanunam, “Pyexplainer: Explaining the predictions of just-in-time defect models,” in 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE) . IEEE, 2021, pp. 407–418
2021
Cited alongside, same era.
S. Lu, D. Guo, S. Ren, J. Huang, A. Svyatkovskiy, A. Blanco, C. Clement, D. Drain, D. Jiang, D. Tang et al. , “Codexglue: A machine learning benchmark dataset for code understanding and generation,” arXiv preprint arXiv:2102.04664 , 2021
Original
2021
Cited alongside, same era.

Then

Y. Wang, W. Wang, S. Joty, and S. C. Hoi, “Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,” arXiv preprint arXiv:2109.00859 , 2021
Original
2021
Later among the works it cites.
C. Tantithamthavorn, J. Jiarpakdee, and J. Grundy, “Actionable analytics: Stop telling me what it is; please tell me what to do,” IEEE Software , vol. 38, no. 4, pp. 115–120, 2021
2021
Later among the works it cites.
C. K. Tantithamthavorn and J. Jiarpakdee, “Explainable ai for software engineering,” in 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE) . IEEE, 2021, pp. 1–2
2021
Later among the works it cites.
J. Jiarpakdee, C. K. Tantithamthavorn, and J. Grundy, “Practitioners’ perceptions of the goals and visual explanations of defect prediction models,” in 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR) . IEEE, 2021, pp. 432–443
2021
Later among the works it cites.
D. Rajapaksha, C. Tantithamthavorn, J. Jiarpakdee, C. Bergmeir, J. Grundy, and W. Buntine, “Sqaplanner: Generating data-informed software quality improvement plans,” IEEE Transactions on Software Engineering , vol. 48, no. 8, pp. 2814–2835, 2021
2021
Later among the works it cites.
C. Pornprasit and C. K. Tantithamthavorn, “Jitline: A simpler, better, faster, finer-grained just-in-time defect prediction,” in 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR) . IEEE, 2021, pp. 369–379
2021
Later among the works it cites.
C. Pan, M. Lu, and B. Xu, “An empirical study on software defect prediction using codebert model,” Applied Sciences , vol. 11, no. 11, p. 4793, 2021
2021
Later among the works it cites.
K. Cao, C. Chen, S. Baltes, C. Treude, and X. Chen, “Automated query reformulation for efficient search based on query logs from stack overflow,” in 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) . IEEE, 2021, pp. 1273–1285
2021
Later among the works it cites.
N. Jiang, T. Lutellier, and L. Tan, “Cure: Code-aware neural machine translation for automatic program repair,” in 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) . IEEE, 2021, pp. 1161–1173
2021
Later among the works it cites.
R. Tufano, S. Masiero, A. Mastropaolo, L. Pascarella, D. Poshyvanyk, and G. Bavota, “Using pre-trained models to boost code review automation,” in Proceedings of the 44th International Conference on Software Engineering , 2022, pp. 2291–2302
2022
Closest in time.
P. Thongtanunam, C. Pornprasit, and C. Tantithamthavorn, “Autotransform: Automated code transformation to support modern code review process,” in Proceedings of the 44th International Conference on Software Engineering , 2022, pp. 237–248
2022
Closest in time.
Y. Liu, C. Tantithamthavorn, Y. Liu, P. Thongtanunam, and L. Li, “Autoupdate: Automatically recommend code updates for android apps,” arXiv preprint arXiv:2209.07048 , 2022
Original
2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…