The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
IntelliCode compose: code generation using transformer
Open accessAbstract
In software development through integrated development environments (IDEs), code completion is one of the most widely used features. Nevertheless, majority of integrated development environments only support completion of methods and APIs, or arguments.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Several methods have been proposed to incorporate repository context into the training of language models, including n-grams (Tu et al., 2014), LSTMs (Hellendoorn and Devanbu, 2017), and Transformers (Svyatkovskiy et al., 2020;Liu et al., 2022;Ding et al., 2022).”
From RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation (2023) · cites this paper as Svyatkovskiy et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The IntelliCode Compose system uses the term CTR (Click Through Rate) for this and reports a value of 10% in online trials [11].”
From Productivity Assessment of Neural Code Completion (2022) · cites this paper as [11]
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“act syntax tree (AST) or concrete syntax tree (CST), and dataflow graph. A transformer block will typically consist of a multi-head self-attention, followed by a two-layer multi-layer perceptron (MLP) [17], optionally containing residual connections and layer normalization [23]. Recent neural architecture searches of t…”
MethodBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 2×
“Several transformer models such as GPT-2, BERT, XLNet, and RoBERTa [19–22] have demonstrated the ability to learn effectively from unlabeled data to perform a wide variety of downstream tasks given supervised discriminative fine-tuning on each specific task.”
BackgroundBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 2×
“Several transformer models such as GPT-2, BERT, XLNet, and RoBERTa [19–22] have demonstrated the ability to learn effectively from unlabeled data to perform a wide variety of downstream tasks given supervised discriminative fine-tuning on each specific task.”
BackgroundRoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · cited 2×
“We refer the interested reader to the numerous publications about transformer models [16, 20–22], and focus on code completion for the remainder of this section.”
BackgroundDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“lue and are most likely lower than the actual user sentiment. Over 150K requests, we have seen a surfacing rate of 9.2% and an acceptance rate of 10%. 11 Knowledge Distillation Knowledge distillation [38] is the model compression technique in which a smaller model – the student network – is trained to reproduce the re…”
InfluentialExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“(3) Language specific control codes, is an approach introduced in [29, 30] that uses target prefixes to facilitate constrained language modeling or multitask learning.”
Background(2004) · Cited by 9,718
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687 · cited 3×
“Transformers [18–21] are a family of neural networks designed to process ordered sequential data.”
BackgroundDistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653 · cited 1×
“n [38] is the model compression technique in which a smaller model – the student network – is trained to reproduce the results of a larger model – the teacher network. It has been shown in literature [39, 40], that it is possible to reach comparable performance on various tasks using distilled neural networks, resulti…”
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.03771 · Cited by 3,347
Research works printed but not linked: 7
- Alexey Svyatkovskiy , Sebastian Lee , Anna Hadjitofi , Maik Riechert , Juliana Franco , and Miltiadis Allamanis . Fast and memory-eficient neural code completion , 2020 . Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi, Maik Riechert, Juliana Franco, and Miltiadis Allamanis. Fast and memory-eficient neural code completion, 2020.
- Alec Radford , Jef Wu , Rewon Child , David Luan , Dario Amodei , and Ilya Sutskever . Language models are unsupervised multitask learners . 2019 . Alec Radford, Jef Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. 2019.
- Microsoft Corporation . Ai-assisted development. https://marketplace. visualstudio.com/items?itemName=VisualStudioExptTeam.VSIntelliCode. Visited Jan 2020 . Microsoft Corporation. Ai-assisted development. https://marketplace. visualstudio.com/items?itemName=VisualStudioExptTeam.VSIntelliCode. Visited Jan 2020.
- Alec Radford . Improving language understanding by generative pre-training . 2018 . Alec Radford. Improving language understanding by generative pre-training. 2018.
- Jimmy Lei Ba , Jamie Ryan Kiros, and Geofrey E. Hinton. Layer normalization , 2016 . Jimmy Lei Ba, Jamie Ryan Kiros, and Geofrey E. Hinton. Layer normalization, 2016.
- Eclipse Foundation . Code Recommenders . www.eclipse.org/recommenders. Visited June 2017 . Eclipse Foundation. Code Recommenders. www.eclipse.org/recommenders. Visited June 2017.
- Eclipse Recommenders . Eclipse SnipMatch . http://www.eclipse.org/ recommenders/manual/#snipmatch , 2014 . Visited Jun 2017. Eclipse Recommenders. Eclipse SnipMatch. http://www.eclipse.org/ recommenders/manual/#snipmatch, 2014. Visited Jun 2017.
Cited by
Sorted by citations
Items 401–480 of 480
Recommending TEE-based Functions Using a Deep Learning Model
Lim, S. (2021) · VTechWorks (Virginia Tech)
Peer Review #3 of "Code4ML: a large-scale dataset of annotated Machine Learning code (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1230v0.1/reviews/3
Peer Review #2 of "Code4ML: a large-scale dataset of annotated Machine Learning code (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1230v0.1/reviews/2
Peer Review #1 of "Code4ML: a large-scale dataset of annotated Machine Learning code (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1230v0.1/reviews/1
Procko, T., & Collins, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4571367
Zhao, G., Fang, G., Du, D., Gao, Q. Z., & Zhang, M. (2023) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs60937.2023.00046
“They have a wide range of applications in NLP, including code generation[35], question answering[36], and language translation[34].”
BackgroundBatwing Compiler: An Artificial Intelligence based Compiler
Harshithan, K. S. (2023) · International Conference on Advances in Computational Intelligence and Communication (ICACIC) · doi:10.1109/icacic59454.2023.10434977
“Svyatkovskiy, Alexey, et al. (2020) provide IntelliCode Compose in their work [15].”
BackgroundHuang, Z., Dutta, S., & Misailovíc, S. (2024) · International Journal on Software Tools for Technology Transfer · doi:10.1007/s10009-024-00737-2
“Other systems like [68] are designed for edit-time code completion in IDEs.”
SYNC: A Structurally Guided Hard Negative Curricula for Generalizable Neural Code Search
Naik, A., Das, S., Vedurada, J., & Aditya, S. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-main.7
“For neural code search, both encoder-only and encoder-decoder pretrained architectures (Kanade et al., 2019; Feng et al., 2020) perform well, with decoder-only models (Svyatkovskiy et al., 2020; Lu et al., 2021) being more successful for generative tasks (Guo et al., 2022).”
MethodRe2GCC: Retrieve-Rerank-Generate Framework for Code Completion
Du, S., Wang, Q., & Jia, D. (2023) · International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR) · doi:10.1109/aihcir61661.2023.00020
“To overcome the limitations, subsequent studies explored the application of deep neural networks [6,7,8] and pre-training approaches[9,10], which have gained popularity in the field of code completion.”
BackgroundA Survey on Code Pre-Trained Models for Neural Program RepairPreprint
Zhan, S., Wang, X., Wei, D., & Cao, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4831589
Programming Language Models in Multilingual Settings
Katzy, J. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3639478.3639787
“In the context of multilingual models, research indicates that training with a mix of languages may be beneficial, especially for resource-scarce languages [4, 8, 9].”
BackgroundTopical: Automatic Repository Tagging using Attention on Hybrid Code Embeddings
Lherondelle, A., Babbar, V., Satsangi, Y., Silavong, F., Eloul, S., & Moran, S. (2024) · doi:10.1145/3643665.3648047
“This can lead to the presence of noisy signals within the representation, complicating the extraction of meaningful information.”
BackgroundRethinking the Role of Structural Information: How It Enhances Code Representation Learning?
Sun, Q., Chen, N., Wang, J., & Li, X. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651132
“Moreover, GPT-like models, such as GPT-C (44), CodeGPT (9) and CodeX (45) are designed to specialize in generative tasks, e.g. , program synthesis and completion.”
MethodOjha, P. R. (2024) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit241051031 · Cited by 1
Malheiros, P. S., Lima, R. R., & Oran, A. C. (2024) · Brazilian Symposium on Software Quality (SBQS) · doi:10.1145/3701625.3701656 · Cited by 4
Beam Search for Improvement of Code Generation in Answering Programming Questions with Code
Fedrushkov, D., Kovalchuk, S. V., Lomshakov, V., & Aliev, A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-73372-7_14
Enhancing Large Language Models for Improved Code Clone Detection: A Fine-Tuning Approach
Amin, R., Nashaat, M., Eid, A., & Abdel-Kader, R. F. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-9327-3_30
UNA: Improving Automated PL-NL System by A Unified Neural Architecture
Yuan, D., Zhang, T., & Jiang, H. (2025) · IEEE Transactions on Reliability · doi:10.1109/tr.2025.3541087
“The source code vocabulary expands to over 240 000 tokens, with more than 65% being rare words, highlighting a critical scalability issue for large-scale software projects [52].”
AI-Powered Tools to Enhance the Stages of Software Development
Adeyinka, T. I., & Adeyinka, K. I. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9356-7.ch006
Data-Driven Security Frameworks: AI-Infused Digital Twin Software Solutions for IoT
Babu, B. S., Joseph, A. S. K., Premalatha, J., Alisha, M., Chekuri, N., & Saravanan, V. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.1721
“Through special issues, prominent scientific publications such as Science and Nature began to discuss the possibilities and difficulties of large data [7, 8].”
Nguyen, K. N. A., Jahan, S., & Slavin, R. (2025) · ACM Symposium on Applied Computing · doi:10.1145/3672608.3707740
“Prominent examples include code generation [19, 27] and mathematical problem solving [31].”
From NL2SQL to NL2Code: Exploring A New Paradigm for Natural Language to Programming Code Generation
Tang, L., Hu, Z., & Liu, Y. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5373-7_90
HDFG: Ethereum Smart Contract Honeypot Detection Based on Pre-Training Techniques
Song, J., Li, Z., Qin, Y., Wang, B., Xiong, G., & Miao, H. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033607
An Android API Recommendation Approach Based on API Dependency Paths Learning
Jia, D., Liu, J., Liu, Y., Yin, Y., & Xiao, Y. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70159
“These approaches often focus on capturing contextual relationships [7–9].”
HyRACC: A Hybrid Retrieval-Augmented Framework for More Efficient Code Completion
Li, C., Shang, J., Feng, Y., & Luo, B. (2025) · IEEE/ACM International Conference on AI Foundation Models and Software Engineering (FORGE) · doi:10.1109/forge66646.2025.00013
Xie, Z. (2025) · Applied and Computational Engineering · doi:10.54254/2755-2721/2025.po24517
BRIDGING DESIGN AND DEVELOPMENT: BUILDING A GENERATIVE AI PLATFORM FOR AUTOMATED CODE GENERATION
Chennamsetty, C. S. (2025) · INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY · doi:10.34218/ijcet_16_02_038
An enhanced approach for automatic annotation of error codes based on Seq2edit.
Wang, J., Lin, T., Zhao, R., & Zhao, H. (2025) · Europe PMC (PubMed Central) · doi:10.7717/peerj-cs.3024
“Svyatkovskiy et al. (2020) proposed the GPT-C model, which applied the generative pre-trained Tranformer (GPT) architecture for code correction attempts.”
Transforming natural language into code: advancing automated code synthesis for software development
shboul, B. A., Qaqour, A., Bani-Salameh, H., & Almakadmeh, K. (2025) · Cluster Computing · doi:10.1007/s10586-025-05688-0
“It has shown great potential for improving automated tools and aid software development processes [ 15 ].”
A Novel Deep Learning-Based Technique for Automatic Source Code Summarization
Shruthi, D., Chethan, H. K., & Ikechukwu, A. V. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06674-9_51
Quantifying cross-language code reuse via function-level clone detection
Rong, Y., & Zhou, Y. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00362-2
“For instance, fine-tuned CodeBERT achieved an F1 of 0.95 on BigCloneBench clones, learning generalizable patterns of similarity (Svyatkovskiy et al. 2020).”
InfluentialAn Empirical Study of Parameter-Efficient Fine-Tuning in Code Change Learning and Beyond
Liu, S., Keung, J., Jin, Z. G., Yang, Z., Liu, F., & Zhang, H. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3637335 · Cited by 1
“Decoder-only models of code, like GPT-C [86], CodeGen [87], Code Llama [88], and Qwen2.”
The price of precision: the cost of preprocessing for automated code revision in code review
Pirouzkhah, S., Rani, P., Sovrano, F., Hellendoorn, V. J., & Bacchelli, A. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10781-4
“Their findings underscored the pivotal role of pre-training, e . g ., the generic Masked Language Model (MLM) objective often surpassed the performance of more tailored objectives (Svyatkovskiy et al. 2020).”
Automated Code Generation Algorithm Using GPT-Based Language Models for Secure Software Development
Obbayed, S., Kumaraswamy, B., V.Hemamalini, Madhuri, T. N. P., Bhuvaneshwari, K. S., Adnan, M. M., & Saadi, M. A. M. A. (2025) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr67387.2025.11291744
Revolutionizing Software Development with Machine Learning: A Comprehensive Review
Kaur, C., Kapur, S., Vandana, V., & Agrawal, T. (2025) · IEEE Space, Aerospace and Defence Conference (SPACE) · doi:10.1109/space65882.2025.11171421
“For example, [1] showed that AI-based code completion tools can accelerate the development process by offering relevant code snippets in real time.”
DS-Generator: Generating Software Metrics for Subsequent Versions of a Software System
Pandey, S. K., Agarwal, A., Ranjan, A., & Tripathi, A. K. (2025) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3727967.3756823
Jin, H., & Hamdaqa, M. (2025) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3756681.3756954 · Cited by 1
CodeWisp: AST Guided Retrieval Augmented Generation for Code Generation and Completion
Atrassi, H. E., Idrissi, Y. E., & Benkaouz, Y. (2025) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom65874.2025.11313399
“In particular, the advent of large language models (LLMs) has enabled intelligent assistants capable of performing tasks such as code autocompletion, bug detection, documentation generation, and natural language interaction [1].”
Zhang, K., Yuan, Z., & Xiong, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-08560-3_34
“For text, the applications include machine translation [3], code generation [38], natural language generation [11], etc.”
Boddupally, H. (2023) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset2310370
AI-based code generation and analysis: A paradigm shift in software development
Rupendra, J., & Shakshi, S. (2025) · i-manager’s Journal on Software Engineering · doi:10.26634/jse.20.1.22554
Enhancing Software Vulnerability Analysis via Large Language Models: A Systematic Review
Wang, L., Li, J., Li, Z., Lu, S., & Yang, G. (2025) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc67331.2025.00092
“In 2020, Microsoft introduced GPT-C [11], its first programming-focused LLM, based on GPT-2 [12] and retrained on a large multilingual code corpus, achieving strong Python code completion performance.”
Adithya, V., S, R. K. J., & Babu, N. V. (2025) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca66444.2025.11383462
“Automation of workflows that include testing has been taken care of in a number of specialized ways [7].”
Challenges of deploying code embeddings: an industrial case study on method name generation
Fein, B., Jungwirth, M., Fraser, G., & Kandlinger, F. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00592-2 · Cited by 1
“It has been shown that transformers can be used to assist with tasks in the domain of source code processing (Feng et al. 2020; Ciniselli et al. 2021; Chirkova and Troshin 2021; Degiovanni and Papadakis 2022; Svyatkovskiy et al. 2020).”
Thota, M. R. (2022) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst2295163 · Cited by 1
Advancing NLIDB Systems with T5-RAG: An Encoder-Decoder Approach to SQL Query Generation
Potdar, M., Potdar, M., & Potdar, S. (2025) · International Conference on Electronics and Computing, Communication Networking Automation Technologies (ICEC2NT) · doi:10.1109/icec2nt65402.2025.11380122
Human–Machine Teaming Agents: A Future Perspective
Teichmann, M., Ragni, M., Vitay, J., Gaedke, M., & Hamker, F. H. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-032-03488-5_30
AI-Augmented Quality Assurance for Enterprise Software Systems
Singireddy, S. R., Sivagnanam, A. M., & Surianarayanan, G. (2025) · IEEE International Conference on Emerging Trends in Computing and Communication (ETCOM) · doi:10.1109/etcom66606.2025.11436286
“3) Feedback and Optimization Layer – applies reinforcement learning to continuously retrain and fine-tune model accuracy based on execution outcomes [11].”
Jing, Z., Cao, C., Liu, Z., Yan, H., & Sun, J. (2026) · Computing · doi:10.1007/s00607-026-01616-1
Developers and generative AI: A study of self-admitted usage in open source projects
Tufano, R., Pepe, F., Zampetti, F., Mastropaolo, A., Dabić, O., Penta, M. D., & Bavota, G. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10848-w · Cited by 2
“…surge of Artificial Intelligence (AI) in SE, researchers shifted their attention towards the more complex generative tasks, such as code generation (Svyatkovskiy et al., 2020; Ciniselli et al., 2021), code review (Tufano et al., 2021, 2022; Li et al., 2022; Thongtanunam et al., 2022), and…”
AI-Driven Code Synthesis for Embedded Systems
Haripriya, S., Vijay, S., Sanika, A. M., & Paramanandam, K. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11467836
“Another Another work, IntelliCode Compose, presented by Svyatkovskiy et al. [3], is grounded on a variant of GPT-2 (GPT-C).”
Integrating Retrieval Augmentation and Decoding Intervention for Automated Program Repair
Wang, S., Lu, L., Qiu, S., Liang, Z., & Suo, S. (2026) · Expert Systems · doi:10.1111/exsy.70251 · Cited by 1
“…by these techniques, decoding intervention has also been applied in software engineering tasks, including code translation, program synthesis and debugging (Chen et al. 2021; Svyatkovskiy et al. 2020), where domain constraints help generate syntactically valid and semantically consistent code.”
A Documentation-Driven Framework for AI-Assisted Full-Circle Agile Software Development
Meng, H., Yu, X., Xu, M., & Zhang, W. (2025) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir67391.2025.11491045
“1) Content Management System: In a multi-tenant content management system (CMS) project, we demonstrated the framework’s capability in systematic refactoring and optimization [6], [14].”
InfluentialFrom Words to Queries: A Comparative Evaluation of GPT Models in NLIDB Systems
Potdar, M., Potdar, M., & Potdar, S. (2026) · IEEE International Conference for Convergence in Computing Technology (I3CTCON) · doi:10.1109/i3ctcon68242.2026.11507817
AdaptGen: A Problem-Adaptive Solution Template Generation Technique for Online Programming Platforms
Zhang, G. T., Zou, W., Zhang, X., Zhang, J., & Xuan, J. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3692192
“Research on generating solution templates for online programming platforms is limited, though it intersects with the broader field of code generation, including tasks like code completion, program synthesis, and code repair [13], [22], [23], [24], [25].”
UVIX AI: Context-Aware Conversational Intelligence for Software Development
Tejaswa Singh Sengar, A. V., & Kushwa, S. S. J. S. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-35277
Context-Aware Pipeline for Automated Code Review Using Large Language Models
Abdalgalil, F., Sherif, G., Mohamed, M., Maragaa, N., & Shawky, D. (2025) · International Conference on Computer Theory and Applications (ICCTA) · doi:10.1109/iccta68914.2025.11520024
“More generally, models such as CodeGPT, GPT-C, and Codex are pre-trained with decoder-only architectures, which makes them effective for synthesis but unsuitable for evaluative review [7], [8].”
From brittle to robust: Improving LLM annotations for SE optimization
Senthilkumar, L., & Menzies, T. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10823-5
“LLMs are used in code generation [58] and testing [13].”
UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning
Ye, F., Ge, J., Li, C., Huang, L., & Luo, B. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797067
“Particularly in the wave of agent-based automated software development, leveraging Retrieval-Augmented Generation (RAG) to dynamically organize context has become a standard configuration and critical infrastructure for assisting code generation [42, 49].”
Can LLMs Keep Up with Library Changes? An Exploratory Study on LLM-Generated Code
Lin, X., Liu, J., & Bao, L. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner67736.2026.00088
“With the continuous advancement of artificial intelligence, Large Language Models (LLMs) have significantly advanced the software development process, including code generation [1]–[3], code completion [4]–[6], and bug fixing [7], [8].”
Deep Feature Learning with Concatenated Rectified Pooling Units
Siddiqui, H., Banerjee, C., Blasch, E., Pasiliao, E. L., & Mukherjee, T. (2026) · Big Data Mining and Analytics · doi:10.26599/bdma.2025.9020079
VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection
Biringa, C. U., Abbas, A., Selvaraj, V., & Kul, G. (2026) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn69566.2026.00043
“IntelliCode Compose [19] introduced an auto-completion tool for completing code with the capacity to generate multiple lines of syntactically correct responses to a code prompt.”
Understanding and Improving ML-based Static Analysis Result Classification via Explainable AI
Yerramreddy, S., Rafieian, M., Wei, S., & Porter, A. (2026) · IEEE International Conference on Software Testing, Verification and Validation (ICST) · doi:10.1109/icst69053.2026.00043
“For instance, Kharkar et al. [10] evaluated the effectiveness of the CodeBERT model [32] and the GPT-C model [33] in reducing false alarms for a single static analysis tool.”
Leveraging text generation for enhanced user story quality
dos Santos, C. A., & Bouchard, K. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00641-w
“Most recently, the code completion systems are evolving to predict longer sequence of tokens and so better support the activity of writing code (Svyatkovskiy et al. 2020; Peng et al. 2023 ).”
On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study
Vitale, A., Guglielmi, E., Scalabrino, S., & Oliveto, R. (2026) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1145/3794763.3794794
“We focus on the latter, which includes code summarization [2, 21, 29, 36], code completion [11, 54], and automated bug fixing [10, 56].”
UMLCoder: A Novel Multi-Agent Framework for Generating Code with the Help of uml Diagrams
Mao, K., Lin, R., Lu, G.-Y., Li, Z., & Hu, B. (2026) · 2026 6th International Conference on Intelligent Communications and Computing (ICICC) · doi:10.1109/icicc71012.2026.11637859
“To overcome these challenges, researchers have increasingly explored multi-agent frameworks to enhance code generation correctness [7], [9].”
Ashif, A. (2026) · IT Professional · doi:10.1109/mitp.2026.3701936
Enhancing code smell classification with code refactoring-based data augmentation
Nizam, A., Aydin, M., İslamoğlu, E., Sahmoud, S., & ÖZAYDIN, Ş. B. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02859-2
“The model architecture, tokenization, and training procedure result in the generation of numerous hyperparameters, the tuning of which is essential for the optimization of predictive performance [58].”
Deep Learning-Based Code Intelligence: A Survey and Practical Analysis
Li, X. (2026) · International Conference on Software Engineering and Computer Applications · doi:10.1145/3829641.3829677
Analyzing and fixing code generation errors of foundation large language models
Wen, H., Zhu, Y., Liu, C. C., Ren, X., Weiwei, D., Yan, M., & Zhang, H. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10958-5
Dhingra, A., Menon, G., & Antony, A. (2026) · IEEE Access · doi:10.1109/access.2026.3741017
“Transformer-based language models [6] scaled into few-shot learners [7] and, trained on code, into practical program synthesizers such as Codex [1] and IntelliCode Compose [8].”
Dijkhuis, T. B., Arends, J. J., & Groenboom, H. M. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-41234-8_1
Shaikh, F. N., & Kakade, R. K. (2026) · International Journal of Innovations in Science Engineering and Management. · doi:10.69968/ijisem.2026v5i4206-213
An Empirical Study of the Non-determinism of ChatGPT in Code Generation
Ouyang, S., Zhang, J. M., Harman, M., & Wang, M. (2023) · arXiv · doi:10.48550/arxiv.2308.02828
“As mentioned in Section 2, we especially focus on the code generated with Python3 language, since it is one of the most widely studied programming languages in code generation [4, 12, 17, 36, 59, 61, 64].”
BackgroundCodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Lu, S., Guo, D., Ren, S., Huang, J., Svyatkovskiy, A., Blanco, A., Clement, C., Drain, D., Jiang, D., Tang, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.04664 · Cited by 536
“Similarly, developers who are confused about what to write next can use code completion systems [57, 1, 56, 66, 67, 8, 27, 7] to automatically complete the following tokens based on the edits made to the code.”
BackgroundMethodInfluentialSelf-citationGraphCodeBERT: Pre-training Code Representations with Data Flow
Guo, D., Ren, S., Lu, S., Feng, Z., Tang, D., Liu, S., Zhou, L., Duan, N., Svyatkovskiy, A., Fu, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.08366 · Cited by 480
“Existing works (Kanade et al., 2019; Karampatsis & Sutton, 2020; Feng et al., 2020; Svyatkovskiy et al., 2020; Buratti et al., 2020) regard a source code as a sequence of tokens and pre-train models on source code to support code-related tasks such as code search, code completion, code summarization, etc.”
BackgroundSelf-citationCodeBLEU: a Method for Automatic Evaluation of Code Synthesis
Ren, S., Guo, D., Lu, S., Zhou, L., Liu, S., Tang, D., Sundaresan, N., Zhou, M., Blanco, A., & Ma, S. (2020) · arXiv · doi:10.48550/arxiv.2009.10297 · Cited by 214
“As code artificial intelligence receives more and more attention (Allamanis et al. 2015; Yin and Neubig 2017; Al-lamanis et al. 2018; Monperrus 2018; Alon et al. 2019; Svyatkovskiy et al. 2020), the evaluation of code synthesis becomes critical to promote its development.”
BackgroundSelf-citation
Metadata
- Authors
- Svyatkovskiy, A., Deng, S. K., Fu, S., & Sundaresan, N.
- Affiliations
- Microsoft (United States) (US)
- Microsoft, USA
- ORCID
- Sundaresan, Neel
- Venue
- Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
- Publisher
- ACM
- Published
- 2020-11-08
- Pages
- 1433-1443
- OpenAlex
- W3025993830
- Cited by
- 474
- References
- 38
- Citations by year
- 2026: 42 · 2025: 97 · 2024: 117 · 2023: 103 · 2022: 52 · 2021: 56 · 2020: 7
- FWCI
- 41.33
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Keywords
- code generation, code completion, transformer models, integrated development environment
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
