CoChat

Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps

Open access
Lo, David · 2023 · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE)
Cited by 40

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

For decades, much software engineering research has been dedicated to devising automated solutions aimed at enhancing developer productivity and elevating software quality. The past two decades have witnessed an unparalleled surge in the development of intelligent solutions tailored for software engineering tasks. This momentum established the Artificial Intelligence for Software Engineering (AI4SE) area, which has swiftly become one of the most active and popular areas within the software engiueering field. This Future of Software Engineering (FoSE) paper navigates through several focal points. It commences with a succinct introduction and history of AI4SE. Thereafter, it underscores the core challenges inherent to AI4SE, particularly highlighting the need to realize trustworthy and synergistic AI4SE. Progressing, the paper paints a vision for the potential leaps achievable if AI4SE's key challenges are surmounted, suggesting a transition toward Software Engineering 2.0. Two strategic roadmaps are then laid out: one centered on realizing trustworthy AI4SE, and the other on fostering synergistic AI4SE. While this paper may not serve as a conclusive guide, its intent is to catalyze further progress. The ultimate aspiration is to position AI4SE as a linchpin in redefining the horizons of software engineering, propelling us toward Software Engineering 2.0.

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/icse-fose59343.2023.00010

Cites

35 of 35 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 35 references

Research works printed but not linked: 122

  1. Johnson, 1977, Lint, a C program checker, Computing Science TR, 65
  2. 10.1007/bfb0025774 · DOI · Paper page
  3. 10.1007/3-540-11494-7_22 · DOI · Paper page
  4. 10.1145/96267.96279 · DOI · Paper page
  5. Bengio, 2016, Springtime for AI: The rise of deep learning
  6. 10.1109/MC.2009.256 · DOI
  7. 10.1145/1181775.1181808 · DOI
  8. 10.1145/1572272.1572290 · DOI
  9. 10.1145/1368088.1368151 · DOI · Paper page
  10. Binkley, 2010, Development: Information retrieval applications, 231
  11. 10.1109/TSE.2012.63 · DOI · Paper page
  12. 10.1016/0950-5849(88)90061-4 · DOI
  13. 10.1145/1039174.1039188 · doi:10.1145/1039174.1039188
  14. Harman, 2009, Search Based Software Engineering - First International Symposium, SSBSE 2009
  15. 10.1145/2693208.2693219 · doi:10.1145/2693208.2693219
  16. 10.1109/CSMR.2013.41 · DOI · Paper page
  17. 10.1109/ISSRE.2013.6698918 · DOI · Paper page
  18. 10.1109/compsac.2013.55 · DOI
  19. 10.1109/MSR.2013.6624040 · DOI
  20. 10.1109/ICPC.2015.18 · DOI
  21. 10.1007/s10664-018-9642-5 · DOI
  22. 10.1145/3412845 · DOI
  23. 10.1109/TSE.2019.2906315 · DOI
  24. 10.1109/TSE.2021.3058985 · DOI
  25. 10.1109/ASE.2017.8115681 · DOI
  26. 10.1145/3551349.3560421 · DOI
  27. 10.1109/QRS.2015.14 · DOI · Paper page
  28. 10.1109/MSR.2015.38 · DOI · Paper page
  29. 10.1145/3290353 · DOI · Paper page
  30. Hoang, 2020, CC2Vec: distributed representations of code changes, 518, 10.1145/3377811.3380361 · DOI · Paper page
  31. Majumder, 2018, 500+ times faster than deep learning: a case study exploring faster methods for text mining stackoverflow, 554, 10.1145/3196398.3196424 · DOI
  32. 10.1145/3238147.3238190 · DOI · Paper page
  33. 10.1145/3460319.3464819 · DOI · Paper page
  34. 10.1109/ASE.2019.00011 · DOI
  35. 10.18653/v1/n19–1423 · DOI · Paper page
  36. 10.1109/ICSME46990.2020.00025 · DOI · Paper page
  37. 2023, OpenAI, GPT-4 technical report, abs/2303.08774 · arXiv
  38. 10.1145/2786805.2786809 · DOI · Paper page
  39. 10.1145/2931037.2931051 · DOI · Paper page
  40. McManus, 2023, Friend or foe: Can computer coders trust ChatGPT
  41. Claburn, 2023, ChatGPT creates mostly insecure code, but wont tell you unless you ask
  42. 10.1145/3379597.3387461 · DOI
  43. 10.1201/9780429258985 · DOI · Paper page
  44. 10.1145/1101908.1101949 · DOI · Paper page
  45. 10.1109/TSE.2023.3279125 · DOI
  46. 10.1145/2001420.2001445 · DOI · Paper page
  47. Christakis, 2016, What developers want and need from program analysis: An empirical study, 332, 10.1145/2970276.2970347 · DOI · Paper page
  48. 10.1109/ICSME.2016.67 · DOI
  49. Csikszentmihalyi, 1990, Flow: The Psychology of Optimal Experience
  50. 10.2190/T543-742X-033L-9877 · DOI
  51. 10.1145/3439961.3439982 · DOI
  52. 10.1109/ICSE-SEIP.2019.00030 · DOI
  53. 10.1097/00043764-197005000-00027 · doi:10.1097/00043764-197005000-00027
  54. 10.1109/ICPC.2015.12 · DOI · Paper page
  55. 10.1109/TSE.2014.2362924 · DOI
  56. 10.1038/nrn1201 · DOI · Paper page
  57. 10.1037/h0020071 · DOI · Paper page
  58. 10.1145/3540250.3549087 · DOI
  59. Hu, 2018, Deep code comment generation, 200, 10.1145/3196321.3196334 · DOI · Paper page
  60. Karpathy, 2017, Software 2.0
  61. 10.1109/TSE.2007.256941 · DOI · Paper page
  62. 10.1145/1557019.1557083 · DOI · Paper page
  63. Kruppa, 2023, Google DeepMind CEO says some form of AGI possible in a few years
  64. Grace, 2022, 2022 expert survey on progress in AI
  65. 10.1518/hfes.46.1.50.30392 · doi:10.1518/hfes.46.1.50.30392 · Paper page
  66. 10.1016/S0020-7373(87)80013-5 · DOI · Paper page
  67. 10.1109/TSE.2018.2877678 · DOI · Paper page
  68. 10.1145/3510003.3510152 · DOI
  69. Wang, 2023, Practitioners expectations on code completion, CoRR, abs/2301.03846 · arXiv
  70. 10.1109/ICSE-SEIP58684.2023.00043 · DOI · Paper page
  71. 10.1145/2884781.2884812 · DOI
  72. 10.1109/ASE56229.2023.00023 · DOI
  73. 10.2139/ssrn.4361607 · DOI · Paper page
  74. 10.1145/3485447.3512244 · DOI
  75. 10.1007/s10664-018-9661-2 · DOI
  76. 10.1109/CSMR.2010.18 · DOI · Paper page
  77. 10.1109/icsme52107.2021.00044 · DOI
  78. Zhang, 2023, Cupid: Leveraging ChatGPT for more accurate duplicate bug report detection, arXiv preprint
  79. 10.1145/3635711 · DOI · Paper page
  80. 10.1109/ICSE48619.2023.00181 · DOI · Paper page
  81. 10.1145/3611643.3616244 · DOI
  82. Guo, 2021, Graph-CodeBERT: Pre-training code representations with data flow
  83. 10.1109/SANER53432.2022.00077 · DOI
  84. 10.1145/3597503.3608136 · DOI
  85. Ahmed, 2023, Improving few-shot prompts with relevant static analysis products, arXiv preprint
  86. 10.1109/ASE56229.2023.00031 · DOI
  87. Xia, 2023, Keep the conversation going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT, CoRR, abs/2304.00385 · arXiv
  88. 10.1145/3510003.3510129 · DOI
  89. 10.1145/3585386 · doi:10.1145/3585386
  90. 10.1109/ICSE48619.2023.00063 · DOI
  91. 10.1145/3524610.3527902 · DOI
  92. Mohammadkhani, 2023, A systematic literature review of explainable AI for software engineering, CoRR, abs/2302.06065 · arXiv
  93. 10.1145/2560217.2560219 · DOI · Paper page
  94. 10.1109/ICPC52881.2021.00046 · DOI
  95. 10.1145/3533767.3534398 · DOI
  96. 10.1109/WCRE.2013.6671293 · DOI
  97. 10.1145/2584654 · doi:10.1145/2584654
  98. 10.1145/1993498.1993551 · DOI
  99. 10.1145/2351676.2351718 · doi:10.1145/2351676.2351718
  100. 10.1109/TSE.2013.6 · DOI
  101. Yang, 2023, What do code models memorize? an empirical study on large language models of code, CoRR, abs/2308.09932 · arXiv
  102. 10.1145/3551349.3556964 · DOI · Paper page
  103. 10.1145/3540250.3560883 · DOI
  104. Metz, 2023, Lawsuit takes aim at the way A.I. is built
  105. 10.1109/MC.2019.2907766 · doi:10.1109/mc.2019.2907766
  106. 10.1109/TSE.2002.1019480 · DOI · Paper page
  107. 10.1145/3236024.3236026 · DOI
  108. 10.1109/TSE.2021.3105556 · DOI
  109. 10.1145/3591227 · DOI
  110. Jha, 2023, CodeAttack: Code-based adversarial at-tacks for pre-trained programming language models, 14892
  111. 10.1109/tse.2024.3361661 · DOI · Paper page
  112. Nguyen, 2023, Adversarial attacks on code models with discriminative graph patterns, CoRR, abs/2308.11161 · arXiv
  113. Schuster, 2021, You autocomplete me: Poisoning vulnerabilities in neural code completion, 1559
  114. 10.1109/TSE.2021.3075215 · DOI
  115. 10.1109/ISSRE.2015.7381836 · DOI
  116. 10.1007/s10664-016-9484-y · DOI
  117. 10.1109/ICST46399.2020.00012 · DOI
  118. Satir, 1991, The Satir Model: Family Therapy & Beyond
  119. Lindstrom, 2003, It gets worse before it gets better: Changing to XP, Cutter IT Journal, 16, 12
  120. 10.1109/WCRE.2012.31 · DOI · Paper page
  121. 10.1109/ICSE48619.2023.00055 · DOI · Paper page
  122. 10.1109/CVPR52729.2023.01925 · DOI

Cited by

See all 40

Metadata

Authors
Lo, D.
Venue
2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE)
Publisher
IEEE
Published
2023-05-14
Pages
69-85
OpenAlex
W4392609567
Cited by
40
References
35
FWCI
10.66
Type
conference paper
Language
en
Open access
green

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: Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. https://app.cochat.ai/papers/10.1109/icse-fose59343.2023.00010
The paper
Lo, D. (2023). Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE). https://doi.org/10.1109/icse-fose59343.2023.00010

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.