DeepFix: Fixing Common C Language Errors by Deep Learning
Open accessAbstract
The problem of automatically fixing programming errors is a very active research topic in software engineering. This is a challenging problem as fixing even a single error may require analysis of the entire program. In practice, a number of errors arise due to programmer's inexperience with the programming language or lack of attention to detail. We call these common programming errors. These are analogous to grammatical errors in natural languages. Compilers detect such errors, but their error messages are usually inaccurate. In this work, we present an end-to-end solution, called DeepFix, that can fix multiple such errors in a program without relying on any external tool to locate or fix them. At the heart of DeepFix is a multi-layered sequence-to-sequence neural network with attention which is trained to predict erroneous program locations along with the required correct statements. On a set of 6971 erroneous C programs written by students for 93 programming tasks, DeepFix could fix 1881 (27%) programs completely and 1338 (19%) programs partially.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Artificial intelligence and machine learning approaches have been used for finding and repairing errors in programs, but only very fundamental approaches have been applied to researching programming error messages.
“Artificial intelligence and machine learning approaches have been used for finding and repairing errors in programs [1,20,21] but only very fundamental approaches have been applied to researching PEMs [11].”
From Using Large Language Models to Enhance Programming Error Messages (2023) · cites this paper as [21]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Vinyals, O., Kaiser, L., Koo, T., Petrov, S., Sutskever, I., & Hinton, G. (2014) · arXiv · doi:10.48550/arxiv.1412.7449 · Cited by 464 · see citing works
Flagged first, then by citations
Research works printed but not linked: 14
- Arcuri, A. 2008. On the automation of fixing software bugs. In ICSE Companion , 1003-1006.
- Bahdanau, D.; Cho, K.; and Bengio, Y. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 . · arXiv
- Bhatia, S., and Singh, R. 2016. Automated correction for syntax errors in programming assignments using recurrent neural networks. arXiv preprint arXiv:1603.06129 . · arXiv
- Cho, K.; Van Merri¨ enboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; and Bengio, Y. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In EMNLP , 1724-1734.
- Das, R.; Ahmed, U. Z.; Karkare, A.; and Gulwani, S. 2016. Prutor: A system for tutoring CS1 and collecting student programs for analysis. CoRR abs/1608.03828. · arXiv
- Hindle, A.; Barr, E. T.; Su, Z.; Gabel, M.; and Devanbu, P. 2012. On the naturalness of software. In ICSE , 837-847.
- Le Goues, C.; N., T.; Forrest, S.; and Weimer, W. 2012. GenProg: A generic method for automatic software repair. IEEE Trans. Software Eng. 54 -72.
- Long, F., and Rinard, M. 2016. Automatic patch generation by learning correct code. In POPL , 298-312.
- Piech, C.; Huang, J.; Nguyen, A.; Phulsuksombati, M.; Sahami, M.; and Guibas, L. J. 2015. Learning program embeddings to propagate feedback on student code. In ICML , 1093-1102.
- Pu, Y.; Narasimhan, K.; Solar-Lezama, A.; and Barzilay, R. 2016. sk p: a neural program corrector for moocs. arXiv preprint arXiv:1607.02902 . · arXiv
- Seo, H.; Sadowski, C.; Elbaum, S.; Aftandilian, E.; and Bowdidge, R. 2014. Programmers' build errors: a case study (at Google). In ICSE , 724-734.
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; and Salakhutdinov, R. 2014. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1):1929-1958.
- Sutskever, I.; Vinyals, O.; and Le, Q. V. 2014. Sequence to sequence learning with neural networks. In NIPS , 31043112.
- Xie, Z.; Avati, A.; Arivazhagan, N.; Jurafsky, D.; and Ng, A. Y. 2016. Neural language correction with character-based attention. arXiv preprint arXiv:1603.09727 . · arXiv
Cited by
Sorted by citations
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590 · see citing works
“DeepFix Code Repair The PaLM-Coder 540B model demonstrates impressive performance on the DeepFix code repair task, reaching a compile rate of 82.1%, compared to 71.7% achieved by prior work (Yasunaga & Liang, 2021).”
MethodInfluentialHarnessing the power of llms in practice: a survey on chatGPT and beyond
Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., Zhong, S., Yin, B., & Hu, X. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3649506 · Cited by 644 · see citing works
Le Goues, C., Pradel, M., & Roychoudhury, A. (2019) · Communications of the ACM · doi:10.1145/3318162 · Cited by 410 · see citing works
The Robots Are Here: Navigating the Generative AI Revolution in Computing Education
Prather, J., Denny, P., Leinonen, J., Becker, B. A., Albluwi, I., Craig, M., Keuning, H., Kiesler, N., Kohn, T., Luxton-Reilly, A., et al. (2023) · Proceedings of the 2023 Working Group Reports on Innovation and Technology in Computer Science Education · doi:10.1145/3623762.3633499 · Cited by 396 · see citing works
An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation
Schäfer, M., Nadi, S., Eghbali, A., & Tip, F. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2023.3334955 · Cited by 431 · see citing works
“Neural techniques are rapidly being adopted for solving various Software Engineering problems, with promising results in several domains including code completion [34], [35], [36], [37], [38], program repair [39], [40], [41], and bug-finding [42], [43].”
MethodAutomated Repair of Programs from Large Language Models
Fan, Z., Gao, X., Mirchev, M., Roychoudhury, A., & Tan, S. H. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00128 · Cited by 256 · see citing works
InCoder: A Generative Model for Code Infilling and Synthesis
Fried, D., Aghajanyan, A., Lin, J., Wang, S., Wallace, E., Shi, F., Zhong, R., Yih, W.-T., Zettlemoyer, L., & Lewis, M. (2022) · arXiv · doi:10.48550/arxiv.2204.05999 · Cited by 187 · see citing works
“This includes methods to infer variable types [50, 66], generate unit tests [25], repair programs [30, 70, 20, 71], and verify program correctness [55].”
MethodBig code != big vocabulary: open-vocabulary models for source code
Karampatsis, R.-M., Babii, H., Robbes, R., Sutton, C., & Janes, A. (2020) · Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering · doi:10.1145/3377811.3380342 · Cited by 182 · see citing works
Deep learning similarities from different representations of source code
Tufano, M., Watson, C., Bavota, G., Di Penta, M., White, M., & Poshyvanyk, D. (2018) · Proceedings of the 15th International Conference on Mining Software Repositories · doi:10.1145/3196398.3196431 · Cited by 158 · see citing works
A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research
Watson, C., Cooper, N., Palacio, D. N., Moran, K., & Poshyvanyk, D. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3485275 · Cited by 137 · see citing works
A Survey of Machine Learning for Big Code and Naturalness
Allamanis, M., Barr, E. T., Devanbu, P., & Sutton, C. (2019) · ACM Computing Surveys · doi:10.1145/3212695 · Cited by 150 · see citing works
Kamoi, R., Zhang, Y., Zhang, N., Han, J., & Zhang, R. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00713 · Cited by 82 · see citing works
“…Schick et al., 2023), grammatical error correction (Ng et al., 2014; Lichtarge et al., 2019), factual error correction (Cao et al., 2020; Thorne and Vlachos, 2021), and code repair (Gupta et al., 2017; Mesbah et al., 2019; Bader et al., 2019; Chen et al., 2021; Yasunaga and Liang, 2020, 2021).”
Teaching Large Language Models to Self-Debug
Chen, X., Lin, M., Schärli, N., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2304.05128 · Cited by 77 · see citing works
“Program repair is an area of research concerned with fixing bugs in code, where several neural network models have been developed to handle different types of bugs (Gupta et al., 2017; Yasunaga & Liang, 2021; Gupta et al., 2020; Wang et al., 2018; Le et al., 2022).”
BackgroundMethodSWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2310.06770 · Cited by 72 · see citing works
Deep Reinforcement Learning for Syntactic Error Repair in Student Programs
Gupta, R., Kanade, A., & Shevade, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301930 · Cited by 54 · see citing works
Self-citationSynShine: Improved Fixing of Syntax Errors
Ahmed, T., Ledesma, N. R., & Devanbu, P. (2023) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3212635 · Cited by 38 · see citing works
Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization
Orvalho, P., Janota, M., & Manquinho, V. (2025) · arXiv · doi:10.48550/arxiv.2502.07786 · Cited by 4 · see citing works
- Authors
- Gupta, R., Pal, S., Kanade, A., & Shevade, S.
- Affiliations
- Indian Institute of Science Bangalore (IN)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2017-02-12
- Volume
- 31
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2605202003
- Cited by
- 426
- References
- 2
- Citations by year
- 2026: 16 · 2025: 38 · 2024: 50 · 2023: 66 · 2022: 53 · 2021: 62 · 2020: 49 · 2019: 54 · 2018: 28 · 2017: 10
- FWCI
- 29.62
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- NOT FOUND REPOSITORY (Indian Institute of Science Bangalore) (acceptedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Keywords
- common programming errors, C programming language, sequence-to-sequence models, attention mechanism, student programming, compiler error messages
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
