Identifying the Factors That Influence Trust in AI Code Completion
Pages 1 - 9
Abstract
AI-powered software development tooling is changing the way that developers interact with tools and write code. However, the ability for AI to truly transform software development may depend on developers' levels of trust in these tools, which has consequences for tool adoption and repeated usage. In this work, we take a mixed-methods approach to measure the factors that influence developers' trust in AI-powered code completion. We found that characteristics about the AI suggestion itself (e.g., the quality of the suggestion), the developer interacting with the suggestion (e.g., their expertise in a language), and the context of the development work (e.g., was the suggestion in a test file) all influenced acceptance rates of AI-powered code suggestions. Based on these findings we propose a number of recommendations for the design of AI-powered development tools to improve trust.
References
[1]
Nadia Alshahwan, Jubin Chheda, Anastasia Finegenova, Beliz Gokkaya, Mark Harman, Inna Harper, Alexandru Marginean, Shubho Sengupta, and Eddy Wang. 2024. Automated Unit Test Improvement using Large Language Models at Meta. arxiv:cs.SE/2402.09171.
[2]
Amazon. 2024. ML-powered coding companion for developers - Amazon CodeWhisperer Features. https://aws.amazon.com/codewhisperer/features/
[3]
Matin Amoozadeh, David Daniels, Daye Nam, Aayush Kumar, Stella Chen, Michael Hilton, Sruti Srinivasa Ragavan, and Mohammad Amin Alipour. 2024. Trust in Generative AI among students: An exploratory study. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1. 67–73.
[4]
Johannes Bader, Sonia Seohyun Kim, Frank Sifei Luan, Satish Chandra, and Erik Meijer. 2021. AI in Software Engineering at Facebook. IEEE Software, 38, 4 (2021), 52–61. https://doi.org/10.1109/MS.2021.3061664
[5]
Shraddha Barke, Michael B James, and Nadia Polikarpova. 2022. Grounded copilot: How programmers interact with code-generating models. arXiv preprint arXiv:2206.15000.
[6]
Yoav Benjamini and Daniel Yekutieli. 2001. The control of the false discovery rate in multiple testing under dependency. The Annals of Statistics, 29, 4 (2001), 1165 – 1188. https://doi.org/10.1214/aos/1013699998
[7]
Alexia Cambon, Brent Hecht, Ben Edelman, Donald Ngwe, Sonia Jaffe, Amy Heger, Mihaela Vorvoreanu, Sida Peng, Jake Hofman, and Alex Farach. 2023. Early LLM-based Tools for Enterprise Information Workers Likely Provide Meaningful Boosts to Productivity. MSFT Technical Report. https://www. microsoft. com/en-us/research ….
[8]
Omer Dunay, Daniel Cheng, Adam Tait, Parth Thakkar, Peter C Rigby, Andy Chiu, Imad Ahmad, Arun Ganesan, Chandra Maddila, and Vijayaraghavan Murali. 2024. Multi-line AI-assisted Code Authoring. arXiv preprint arXiv:2402.04141.
[9]
Mary T Dzindolet, Scott A Peterson, Regina A Pomranky, Linda G Pierce, and Hall P Beck. 2003. The role of trust in automation reliance. International journal of human-computer studies, 58, 6 (2003), 697–718.
[10]
Nat Friedman. 2021. Introducing github copilot: Your AI pair programmer. https://github.blog/2021-06-29-introducing-github-copilot-ai-pair-programmer/
[11]
Google. 2024. AI-assisted application development. https://cloud.google.com/duet-ai
[12]
Brittany Johnson, Christian Bird, Denae Ford, Nicole Forsgren, and Thomas Zimmermann. 2023. Make Your Tools Sparkle with Trust: The PICSE Framework for Trust in Software Tools. In 2023 IEEE/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). 409–419.
[13]
Michelle E Kiger and Lara Varpio. 2020. Thematic analysis of qualitative data: AMEE Guide No. 131. Medical teacher, 42, 8 (2020), 846–854.
[14]
Vivian Lai and Chenhao Tan. 2019. On human predictions with explanations and predictions of machine learning models: A case study on deception detection. In Proceedings of the conference on fairness, accountability, and transparency. 29–38.
[15]
John D Lee and Katrina A See. 2004. Trust in automation: Designing for appropriate reliance. Human factors, 46, 1 (2004), 50–80.
[16]
Roger C Mayer, James H Davis, and F David Schoorman. 1995. An integrative model of organizational trust. Academy of management review, 20, 3 (1995), 709–734.
[17]
Hussein Mozannar, Gagan Bansal, Adam Fourney, and Eric Horvitz. 2022. Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming. arXiv preprint arXiv:2210.14306.
[18]
Hussein Mozannar, Gagan Bansal, Adam Fourney, and Eric Horvitz. 2023. When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming. arxiv:cs.HC/2306.04930.
[19]
Emerson Murphy-Hill, Chris Parnin, and Andrew P Black. 2011. How we refactor, and how we know it. IEEE Transactions on Software Engineering, 38, 1 (2011), 5–18.
[20]
John O’Donovan and Barry Smyth. 2005. Trust in recommender systems. In Proceedings of the 10th international conference on Intelligent user interfaces. 167–174.
[21]
Hammond Pearce, Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, and Ramesh Karri. 2022. Asleep at the keyboard? assessing the security of github copilot’s code contributions. In 2022 IEEE Symposium on Security and Privacy (SP). 754–768.
[22]
Neil Perry, Megha Srivastava, Deepak Kumar, and Dan Boneh. 2023. Do users write more insecure code with AI assistants? In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 2785–2799.
[23]
Crystal Qian and James Wexler. 2024. Take It, Leave It, or Fix It: Measuring Productivity and Trust in Human-AI Collaboration. arXiv preprint arXiv:2402.18498.
[24]
Maxim Tabachnyk and Stoyan Nikolov. 2022. ML-enhanced code completion improves developer productivity. https://ai.googleblog.com/2022/07/ml-enhanced-code-completion-improves.html
[25]
Priyan Vaithilingam, Tianyi Zhang, and Elena L Glassman. 2022. Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models. In CHI Conference on Human Factors in Computing Systems Extended Abstracts. 1–7.
[26]
Ming Yin, Jennifer Wortman Vaughan, and Hanna Wallach. 2019. Understanding the effect of accuracy on trust in machine learning models. In Proceedings of the 2019 chi conference on human factors in computing systems. 1–12.
[27]
Yunfeng Zhang, Q. Vera Liao, and Rachel K. E. Bellamy. 2020. Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (FAT* ’20). Association for Computing Machinery, New York, NY, USA. 295–305. isbn:9781450369367 https://doi.org/10.1145/3351095.3372852
[28]
Albert Ziegler, Eirini Kalliamvakou, X Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, and Edward Aftandilian. 2022. Productivity assessment of neural code completion. In Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming. 21–29.
Index Terms
- Identifying the Factors That Influence Trust in AI Code Completion
Recommendations
Re-examining the influence of trust on online repeat purchase intention: The moderating role of habit and its antecedents
Customer loyalty or repeat purchasing is critical for the survival and success of any store. By focusing on online stores, this study investigates the moderating role of habit on the relationship between trust and repeat purchase intention. Prior ...
The Role of Satisfaction as a Moderation of the Influence of Trust on Consumer Loyalty
ICIEB '18: Proceedings of the 2018 1st International Conference on Internet and e-BusinessThis research was conducted to find out the role of satisfaction as moderation of influence of trust to loyalty at MatahariMall.com. Sampling technique that used in this research is non probability sampling technique and data analysis using moderated ...
Do You Trust AI? Examining AI Trustworthiness Perceptions Among the General Public
Artificial Intelligence in HCIAbstractSocietal acceptance and successful adoption of artificial intelligence (AI) hinge critically on our trust in AI technology. Trust becomes particularly crucial in human-AI interaction due to perceived risks arising from AI behaviors’ complexity and ...
Comments
Information & Contributors
Information
Published In
July 2024
182 pages
ISBN:9798400706851
DOI:10.1145/3664646
- General Chairs:
- Bram Adams,
- Thomas Zimmermann,
- Ipek Ozkaya,
- Program Chairs:
- Dayi Lin,
- Jie M. Zhang
Copyright © 2024 Copyright held by the owner/author(s).
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 10 July 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
AIware '24
Sponsor:
AIware '24: 1st ACM International Conference on AI-Powered Software
July 15 - 16, 2024
Porto de Galinhas, Brazil
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 96Total Downloads
- Downloads (Last 12 months)96
- Downloads (Last 6 weeks)96
Reflects downloads up to 10 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in