The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models
Abstract
Recent advances in Large Language Models (LLM) have made automatic code generation possible for real-world programming tasks in general-purpose programming languages such as Python. However, there are few human studies on the usability of these tools and how they fit the programming workflow. In this work, we conducted a within-subjects user study with 24 participants to understand how programmers use and perceive Copilot, a LLM-based code generation tool. We found that, while Copilot did not necessarily improve the task completion time or success rate, most participants preferred to use Copilot in daily programming tasks, since Copilot often provided a useful starting point and saved the effort of searching online. However, participants did face difficulties in understanding, editing, and debugging code snippets generated by Copilot, which significantly hindered their task-solving effectiveness. Finally, we highlighted several promising directions for improving the design of Copilot based on our observations and participants’ feedback.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The closest to our work is the study by Vaithilingam et al. [2022], which also evaluates Copilot.”
From Grounded Copilot: How Programmers Interact with Code-Generating Models (2023) · cites this paper as Vaithilingam et al. [2022]
In the citing paper
“we are aware of only one usability study of Copilot, by Vaithilingam et al. [2022]”
From Grounded Copilot: How Programmers Interact with Code-Generating Models (2023) · cites this paper as Vaithilingam et al. [2022]
In the citing paper
“On the other hand, Vaithilingam et al. [34] showed in a study of 24 participants showed no signifcant improvement in task completion time -yet participants stated a clear preference for Copilot.”
From Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming (2024) · cites this paper as [34]
In the citing paper
“Early assessments suggest that programmers do feel more productive when assisted by the code recommendation models [40] and that they prefer these systems to earlier code completion engines [34].”
From Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming (2024) · cites this paper as [34]
In the citing paper
“In particular, the neural models introduce new tasks into a developer's workfow, such as writing AI prompts [17] and verifying AI suggestions [34], which can be lengthy.”
From Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming (2024) · cites this paper as [34]
37 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The role of trust in automation reliance
Dzindolet, M. T., Peterson, S. A., Pomranky, R. A., Pierce, L. G., & Beck, H. P. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00038-7 · Cited by 1,276
Zhang, Y., Liao, Q. V., & Bellamy, R. K. E. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372852 · Cited by 895
A Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1041 · Cited by 623
A Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · arXiv · doi:10.48550/arxiv.1704.01696 · Cited by 585
Automating string processing in spreadsheets using input-output examples
Gulwani, S. (2011) · ACM SIGPLAN Notices · doi:10.1145/1925844.1926423 · Cited by 581
Why and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552
Oracle-guided component-based program synthesis
Jha, S., Gulwani, S., Seshia, S. A., & Tiwari, A. (2010) · Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering - Volume 1 · doi:10.1145/1806799.1806833 · Cited by 510
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Husain, H., Wu, H.-H., Gazit, T., Allamanis, M., & Brockschmidt, M. (2019) · arXiv · doi:10.48550/arxiv.1909.09436 · Cited by 483
Overtrust of robots in emergency evacuation scenarios
Robinette, P., Li, W., Allen, R., Howard, A. M., & Wagner, A. R. (2016) · 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1109/hri.2016.7451740 · Cited by 468
Program Synthesis with Large Language Models
Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., Le, Q., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07732 · Cited by 388
An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation
Tufano, M., Watson, C., Bavota, G., Penta, M. D., White, M., & Poshyvanyk, D. (2019) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3340544 · Cited by 370
GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow
Black, S., Leo, G., Wang, P., Leahy, C., & Biderman, S. (2021) · Zenodo · doi:10.5281/zenodo.5297715 · Cited by 324
Kocielnik, R., Amershi, S., & Bennett, P. N. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300641 · Cited by 277
Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks
Mastropaolo, A., Scalabrino, S., Cooper, N., Nader Palacio, D., Poshyvanyk, D., Oliveto, R., & Bavota, G. (2021) · 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) · doi:10.1109/icse43902.2021.00041 · Cited by 247
Assessing demand for intelligibility in context-aware applications
Lim, B. Y., & Dey, A. K. (2009) · Proceedings of the 11th international conference on Ubiquitous computing · doi:10.1145/1620545.1620576 · Cited by 246
DeepCoder: Learning to Write Programs
Balog, M., Gaunt, A. L., Brockschmidt, M., Nowozin, S., & Tarlow, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01989 · Cited by 212
Code Prediction by Feeding Trees to Transformers
Kim, S., Zhao, J., Tian, Y., & Chandra, S. (2021) · 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) · doi:10.1109/icse43902.2021.00026 · Cited by 209
FlashExtract: a framework for data extraction by examples
Le, V., & Gulwani, S. (2014) · Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/2594291.2594333 · Cited by 209
Rajeev, A., Rastislav, B., Eric, D., Dana, F., Pranav, G., Garvit, J., Hadas, K.-G., Madhusudan, P., Martin Milo, M. K., Mukund, R., et al. (2015) · NATO Science for Peace and Security Series - D: Information and Communication Security · doi:10.3233/978-1-61499-495-4-1 · Cited by 200
Programming by sketching for bit-streaming programs
Solar-Lezama, A., Rabbah, R., Bodík, R., & Ebcioğlu, K. (2005) · Proceedings of the 2005 ACM SIGPLAN conference on Programming language design and implementation · doi:10.1145/1065010.1065045 · Cited by 195
Inductive programming meets the real world
Gulwani, S., Hernández‐Orallo, J., Kitzelmann, E., Muggleton, S., Schmid, U., & Zorn, B. G. (2015) · Communications of the ACM · doi:10.1145/2736282 · Cited by 188
Interacting meaningfully with machine learning systems: Three experiments
Stumpf, S., Rajaram, V., Li, L., Wong, W.-K., Burnett, M., Dietterich, T., Sullivan, E., & Herlocker, J. (2009) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2009.03.004 · Cited by 184
Programming by Demonstration Using Version Space Algebra
Lau, T., Wolfman, S. A., Domingos, P., & Weld, D. S. (2003) · Machine Learning · doi:10.1023/a:1025671410623 · Cited by 178
TreeGen: A Tree-Based Transformer Architecture for Code Generation
Sun, Z., Zhu, Q., Xiong, Y., Sun, Y., Mou, L., & Zhang, L. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6430 · Cited by 167
In-IDE Code Generation from Natural Language: Promise and Challenges
Xu, F. F., Vasilescu, B., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2101.11149 · Cited by 153
Toolkit to support intelligibility in context-aware applications
Lim, B. Y., & Dey, A. K. (2010) · Proceedings of the 12th ACM international conference on Ubiquitous computing · doi:10.1145/1864349.1864353 · Cited by 143
Perfection Not Required? Human-AI Partnerships in Code Translation
Weisz, J. D., Muller, M., Houde, S., Richards, J., Ross, S. I., Martinez, F., Agarwal, M., & Talamadupula, K. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450656 · Cited by 129
An Empirical Study on the Usage of BERT Models for Code Completion
Ciniselli, M., Cooper, N., Pascarella, L., Poshyvanyk, D., Penta, M. D., & Bavota, G. (2021) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr52588.2021.00024 · Cited by 126
Rousillon: Scraping Distributed Hierarchical Web Data
Chasins, S., Mueller, M., & Bodík, R. (2018) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3242587.3242661 · Cited by 119
Graphical techniques in a spreadsheet for specifying user interfaces
(1991) · doi:10.1145/108844.108903 · Cited by 105
Towards improving trust in context-aware systems by displaying system confidence
Antifakos, S., Kern, N., Schiele, B., & Schwaninger, A. (2005) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/1085777.1085780 · Cited by 103
Synthesizing data structure transformations from input-output examples
Feser, J., Chaudhuri, S., & Dillig, I. (2015) · ACM SIGPLAN Notices · doi:10.1145/2813885.2737977 · Cited by 98
Interactive Program Synthesis by Augmented Examples
Zhang, T., Lowmanstone, L., Wang, X., & Glassman, E. L. (2020) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3379337.3415900 · Cited by 80
Self-citationMaybe Deep Neural Networks are the Best Choice for Modeling Source CodePreprint
Karampatsis, R.-M., & Sutton, C. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.05734 · Cited by 64
Content Enhanced BERT-based Text-to-SQL GenerationPreprint
Guo, T., & Gao, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07179 · Cited by 61
Programming not only by example
Peleg, H., Shoham, S., & Yahav, E. (2018) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3180155.3180189 · Cited by 49
Wang, C., Feng, Y., Bodík, R., Cheung, A., & Dillig, I. (2019) · Proceedings of the ACM on Programming Languages · doi:10.1145/3371117 · Cited by 37
Retrieval-Based Neural Code GenerationPreprint
Hayati, S. A., Olivier, R., Avvaru, P., Yin, P., Tomasic, A., & Neubig, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.10025 · Cited by 29
EAGER: PROGRAMMING REPETITIVE TASKS BY EXAMPLE
Cypher, A. (1995) · Elsevier eBooks · doi:10.1016/b978-0-08-051574-8.50083-2 · Cited by 23
Examining Zero-Shot Vulnerability Repair with Large Language Models
Pearce, H., Tan, B., Ahmad, B., Karri, R., & Dolan-Gavitt, B. (2021) · arXiv · doi:10.48550/arxiv.2112.02125 · Cited by 17
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation
Xu, F. F., Jiang, Z., Yin, P., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.09015
Research works printed but not linked: 5
- 10.5555/3524938.3524962 · doi:10.5555/3524938.3524962
- Mark Chen , Jerry Tworek , Heewoo Jun , Qiming Yuan , Henrique Ponde de Oliveira Pinto , Jared Kaplan, Harri Edwards, Yuri Burda , Nicholas Joseph, Greg Brockman , 2021 . Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374(2021). Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374(2021). · arXiv
- Richard J Waldinger and Richard CT Lee . 1969 . PROW: A step toward automatic program writing . In Proceedings of the 1st international joint conference on Artificial intelligence. 241–252 . Richard J Waldinger and Richard CT Lee. 1969. PROW: A step toward automatic program writing. In Proceedings of the 1st international joint conference on Artificial intelligence. 241–252.
- Daniel S Weld and Gagan Bansal. 2018. Intelligible artificial intelligence. ArXiv e-prints March 2018(2018). Daniel S Weld and Gagan Bansal. 2018. Intelligible artificial intelligence. ArXiv e-prints March 2018(2018).
- Pengcheng Yin and Graham Neubig . 2018 . TRANX: A transition-based neural abstract syntax parser for semantic parsing and code generation. arXiv preprint arXiv:1810.02720(2018). Pengcheng Yin and Graham Neubig. 2018. TRANX: A transition-based neural abstract syntax parser for semantic parsing and code generation. arXiv preprint arXiv:1810.02720(2018). · arXiv
Cited by
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083
Large language models for software engineering: survey and open problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE) · doi:10.1109/icse-fose59343.2023.00008 · Cited by 650
“For example, Vaithilingam et al. [200] reported on the difficulties 24 participants had in understanding, editing, and debugging the Copilot-generated code, while Feldt et al. [133] proposed a hierarchy of design architecture for LLM-based software testing agents.”
MethodLarge Language Models for Software Engineering: Survey and Open Problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · arXiv · doi:10.48550/arxiv.2310.03533 · Cited by 523
GitHub Copilot AI pair programmer: Asset or Liability?
Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., & Jiang, Z. M. (. (2023) · Journal of Systems and Software · doi:10.1016/j.jss.2023.111734 · Cited by 417
Grounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3586030 · Cited by 436
Metadata
- Authors
- Vaithilingam, P., Zhang, T., & Glassman, E. L.
- Affiliations
- Harvard University (US)
- Purdue University West Lafayette (US)
- Venue
- CHI Conference on Human Factors in Computing Systems Extended Abstracts
- Publisher
- ACM
- Published
- 2022-04-27
- Pages
- 1-7
- OpenAlex
- W4225108562
- Semantic Scholar
- 4054fc9e8776dc0324cfc215462d606eb75916c0
- Cited by
- 660
- References
- 33
- Citations by year
- 2026: 157 · 2025: 179 · 2024: 238 · 2023: 79 · 2022: 7
- FWCI
- 112.42
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion)
- Funders
- NSF (National Science Foundation) (2107391)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- large language models, automatic code generation, Copilot, usability, programmer experience, code editing, user preferences, task completion time
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
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.