Page 25 - 《软件学报》2026年第6期

2344 软件学报 2026 年第 37 卷第 6 期

[4] Lacomis J, Yin PC, Schwartz E, Allamanis M, Le Goues C, Neubig G, Vasilescu B. DIRE: A neural approach to decompiled identifier
naming. In: Proc. of the 34th IEEE/ACM Int’l Conf. on Automated Software Engineering. San Diego: IEEE, 2019. 628–639. [doi: 10.
1109/ASE.2019.00064]
[5] Zhang Z, Ye YP, You W, Tao GW, Lee WC, Kwon Y, Aafer Y, Zhang XY. OSPREY: Recovery of variable and data structure via
probabilistic analysis for stripped binary. In: Proc. of the 2021 IEEE Symp. on Security and Privacy (SP). San Francisco: IEEE, 2021.
813–832. [doi: 10.1109/SP40001.2021.00051]
[6] Pei KX, Guan J, Broughton M, Chen ZT, Yao SC, Williams-King D, Ummadisetty V, Yang JF, Ray B, Jana S. StateFormer: Fine-grained
type recovery from binaries using generative state modeling. In: Proc. of the 29th ACM Joint Meeting on European Software Engineering
Conf. and Symp. on the Foundations of Software Engineering. Athens: ACM, 2021. 690–702. [doi: 10.1145/3468264.3468607]
[7] Chen QB, Lacomis J, Schwartz EJ, Goues CL, Neubig G, Vasilescu B. Augmenting decompiler output with learned variable names and
types. In: Proc. of the 31st USENIX Security Symp. Boston: USENIX Association, 2022. 4327–4343.
[8] Katz DS, Ruchti J, Schulte E. Using recurrent neural networks for decompilation. In: Proc. of the 25th Int’l Conf. on Software Analysis,
Evolution and Reengineering (SANER). Campobasso: IEEE, 2018. 346–356. [doi: 10.1109/SANER.2018.8330222]
[9] Fu C, Chen HL, Liu HL, Chen XY, Tian YD, Koushanfar F, Zhao JS. Coda: An end-to-end neural program decompiler. In: Proc. of the
33rd Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 333. [doi: 10.5555/3454287.
3454620]
[10] de Moura L, Bjørner N. Satisfiability modulo theories: Introduction and applications. Communications of the ACM, 2011, 54(9): 69–77.
[doi: 10.1145/1995376.1995394]
[11] Chang TY, Chen SZ, Fan GD, Feng ZY. A self-iteration code generation method based on large language models. In: Proc. of the 29th Int’l
Conf. on Parallel and Distributed Systems (ICPADS). Ocean Flower Island: IEEE, 2023. 275–281. [doi: 10.1109/ICPADS60453.2023.
00049]
[12] Dong YH, Jiang X, Jin Z, Li G. Self-collaboration code generation via ChatGPT. ACM Trans. on Software Engineering and
Methodology, 2024, 33(7): 189. [doi: 10.1145/3672459]
[13] Huang T, Sun ZH, Jin Z, Li G, Lyu C. Knowledge-aware code generation with large language models. In: Proc. of the 32nd IEEE/ACM
Int’l Conf. on Program Comprehension (ICPC). Lisbon: ACM, 2024. 52–63. [doi: 10.1145/3643916.3644418]
[14] Jiang X, Dong YH, Wang LC, Fang Z, Shang QW, Li G, Jin Z, Jiao WP. Self-planning code generation with large language models.
ACM Trans. on Software Engineering and Methodology, 2024, 33(7): 182. [doi: 10.1145/3672456]
[15] Fan ZY, Gao X, Mirchev M, Roychoudhury A, Tan SH. Automated repair of programs from large language models. In: Proc. of the 45th
Int’l Conf. on Software Engineering (ICSE). Melbourne: IEEE, 2023. 1469–1481. [doi: 10.1109/ICSE48619.2023.00128]
[16] Jin M, Shahriar S, Tufano M, Shi X, Lu S, Sundaresan N, Svyatkovskiy A. InferFix: End-to-end program repair with LLMs. In: Proc. of
the 31st ACM Joint European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. San Francisco: ACM,
2023. 1646–1656. [doi: 10.1145/3611643.3613892]
[17] Lemieux C, Inala JP, Lahiri SK, Sen S. CodaMosa: Escaping coverage plateaus in test generation with pre-trained large language models.
In: Proc. of the 45th Int’l Conf. on Software Engineering (ICSE). Melbourne: IEEE, 2023. 919–931. [doi: 10.1109/ICSE48619.2023.
00085]
[18] Yuan ZQ, Liu MW, Ding SJ, Wang KX, Chen YX, Peng X, Lou YL. Evaluating and improving ChatGPT for unit test generation. Proc.
of the ACM on Software Engineering, 2024, 1(FSE): 76. [doi: 10.1145/3660783]
[19] Zou MQ, Khan A, Wu RY, Gao H, Bianchi A, Tian D. D-Helix: A generic decompiler testing framework using symbolic differentiation.
In: Proc. of the 33rd USENIX Security Symp. Philadelphia: USENIX Association, 2024. 397–414.
[20] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the
31st Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010. [doi: 10.5555/
3295222.3295349]
[21] Hosseini I, Dolan-Gavitt B. Beyond the C: Retargetable decompilation using neural machine translation. In: Proc. of the 2022 Workshop
on Binary Analysis Research (BAR). San Diego: The Internet Society, 2022. 1–11. [doi: 10.14722/bar.2022.23009]
[22] Al-Kaswan A, Ahmed T, Izadi M, Sawant AA, Devanbu P, van Deursen A. Extending source code pre-trained language models to
summarise decompiled binaries. In: Proc. of the 30th Int’l Conf. on Software Analysis, Evolution and Reengineering (SANER). Taipa:
IEEE, 2023. 260–271. [doi: 10.1109/SANER56733.2023.00033]
[23] Wang Y, Wang WS, Joty S, Hoi SCH. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and
generation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 8696–8708. [doi:
10.18653/v1/2021.emnlp-main.685]