Investigating and Designing for Trust in AI-powered Code Generation Tools
Open accessAbstract
Trust is a crucial factor for the adoption and responsible usage of generative AI tools in complex tasks such as software engineering. However, we have a limited understanding of how software developers evaluate the trustworthiness of AI-powered code generation tools in real-world settings. To address this gap, we conducted Study 1, an interview study with 17 developers who use AI-powered code generation tools in professional or personal settings. We found that developers’ trust is rooted in the AI tool’s perceived ability, integrity, and benevolence, and is situational, varying according to the context of usage. Existing AI code generation tools lack the affordances for developers to efficiently and effectively evaluate the trustworthiness of AI-powered code generation tools. To explore designs that can augment the existing interface of AI-powered code generation tools, we explored three sets of design concepts (suggestion quality indicators, usage stats, and control mechanisms) that derived from Study 1 findings. In Study 2, a design probe study with 12 developers, we investigated the potential of these design concepts to help developers make effective trust judgments. We discuss the implication of our findings on the design of AI-powered code generation tools and future research on trust in AI.
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
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?
Frustration is caused both by insufficient help and invasive and premature suggestions not aligned with developers' intentions.
“Wang et al. [34] report that frustration is caused both by insufficient help and invasive and premature suggestions not aligned with developers' intentions.”
From How do Copilot Suggestions Impact Developers' Frustration and Productivity? (2025) · cites this paper as Wang et al. [34]
Before a prompt reaches Copilot's filter, two hard-coded rules prevent prompts containing fewer than 10 characters and prompts where the cursor is in the middle of a line (checked by whether there is whitespace after the cursor), except when a closing character such as a closing bracket, quote, or semicolon is on that line.
“Before a prompt reaches the filter, two hard-coded rules prevent (1) prompts containing fewer than 10 characters, and (2) prompts where the cursor is in the middle of a line, by checking whether there is whitespace after the cursor; except if there is a closing character on that line, such as a closing bracket, quote, or semicolon.”
From A Transformer-Based Approach for Smart Invocation of Automatic Code Completion (2024) · cites this paper as [41]
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredCopilot's filter uses a logistic classifier whose features are those listed in Table 6 (as investigated for version v1.57.7193, June 2022).
“Based on [41], we investigated the v1.57.7193 (June 2022) version of Copilot and list the features used in their logistic classifier in Table 6.”
From A Transformer-Based Approach for Smart Invocation of Automatic Code Completion (2024) · cites this paper as [41]
Section F (p. 22) describes Copilot’s code-generation features as of July 2022, but does not discuss a filter or logistic classifier. Searches for the classifier, Table 6 features, and version v1.57.7193 found no passage in our copy addressing those details. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 2× · see citing works
“The recent development of generative AI models [12] unleashes new possibilities for AI-generated content.”
BackgroundMethodReflecting on reflexive thematic analysis
Braun, V., & Clarke, V. (2019) · Qualitative Research in Sport, Exercise and Health · doi:10.1080/2159676x.2019.1628806 · Cited by 19,677 · cited 1× · see citing works
“” P7 echoed the sentiment and worried that “ (AI tool is) robbing me from the opportunity to actually use my brain,” preventing them from improving their own programming skills.”
BackgroundAn integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 7× · see citing works
“Besides contextual factors, prior research identified that three system properties, including the system’s ability, benevolence, and integrity, shape users’ trust [32, 41].”
BackgroundMethodInfluentialTrust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605 · cited 4× · see citing works
“…as the user’s attitude that “an agent will help achieve an individual’s goals in a situation characterized by uncertainty and vulnerability” [33, 36, 56], and therefore is particularly important when users engage in high-stake scenarios where the mistakes could have significant…”
BackgroundInfluentialOn the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · see citing works
Self-citation(2007) · International Linear Collider · Cited by 1,382 · see citing works
Buçinca, Z., Malaya, M. B., & Gajos, K. Z. (2021) · arXiv · doi:10.48550/arxiv.2102.09692 · Cited by 1,124 · see citing works
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
Liao, Q. V., Gruen, D., & Miller, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376590 · Cited by 925 · cited 1× · see citing works
“A related approach is to support the interpretability of model mechanisms [37, 43, 53], increasing the predictability [18, 21] of AI behavior.”
BackgroundZhang, 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 · cited 4× · see citing works
“During the 60-minute retrospective interview sessions, we asked participants about their general experience with AI tools and then asked them to walk through the significant moments they collected during the prior week.”
BackgroundMethodInfluentialWhy Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B., & Yang, Q. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581388 · Cited by 893 · cited 1× · see citing works
“While the specific recommendations are derived from the context of AI code generation tools, we believe our advice can also be useful for supporting users in building and calibrating trust with generative AI applications more broadly.”
BackgroundDurumeric, Z., Li, F., Kasten, J., Amann, J., Beekman, J. G., Payer, M., Weaver, N., Adrian, D., Paxson, V., Bailey, M., et al. (2014) · ACM Internet Measurement Conference (IMC) · doi:10.1145/2663716.2663755 · Cited by 692 · cited 2× · see citing works
“Without proper support, developers can find it challenging to form accurate mental models of what AI tools can do or not [50] or determine the quality of specific AI suggestions [5, 48, 55]; thus becoming vulnerable to over-or under-trusting the AI [22, 46].”
BackgroundVaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660 · cited 5× · see citing works
“Yet, while emerging work has begun investigating the general usability of AI assistant tools in software engineering or in broader domains [8, 9, 53, 56, 59, 68], we still know little about how designers should consider trust when designing system interfaces for AI-powered code generation tools.”
BackgroundInfluentialFormalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545 · cited 6× · see citing works
“Previous research highlighted the importance of context in understanding users’ trust in AI systems [35, 39, 67].”
BackgroundInfluentialOpportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
Das, A., & Rad, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11371 · Cited by 504 · cited 1× · see citing works
“Trust is often considered one of the key factors that affect the interaction between people and AI [17, 20, 41].”
BackgroundAsleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions
Pearce, H., Ahmad, B., Tan, B., Dolan-Gavitt, B., & Karri, R. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833571 · Cited by 476 · see citing works
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 · see citing works
GitHub Copilot AI pair programmer: Asset or Liability?
Dakhel, A. M., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., Ming, Z., & Jiang (2022) · arXiv · doi:10.48550/arxiv.2206.15331 · Cited by 417 · see citing works
Lee, M., Liang, P., & Yang, Q. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502030 · Cited by 345 · cited 1× · see citing works
“Given that trust is deeply embedded in contextual factors, the factors identified in prior empirical studies might change for AI-powered code-generation tools as system properties and the social and organizational contexts of usage shift.”
BackgroundProxy tasks and subjective measures can be misleading in evaluating explainable AI systems
Buçinca, Z., Lin, P., Gajos, K. Z., & Glassman, E. L. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377498 · Cited by 307 · cited 1× · see citing works
“…design of traditional programming support tools, such as compilers and version control systems [62, 63] to ensure software safety [26, 38], developers’ trust in AI code generation tools needs even more nuanced and careful consideration [6, 17, 48] due to the uncertainty introduced by generative AI.”
BackgroundNovice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models
Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376739 · Cited by 271 · cited 2× · see citing works
“This also echoes prior research in the context of AI-powered music generation which indicated that enabling users to steer AI behavior increases trust in AI [39].”
BackgroundResultDo Users Write More Insecure Code with AI Assistants?
Perry, N., Srivastava, M., Kumar, D., & Boneh, D. (2023) · Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3576915.3623157 · Cited by 259 · cited 2× · see citing works
“A related approach is to support the interpretability of model mechanisms [37, 43, 53], increasing the predictability [18, 21] of AI behavior.”
BackgroundMethodThe Trustworthy Computing Security Development Lifecycle
Lipner, S. (2005) · 20th Annual Computer Security Applications Conference · doi:10.1109/csac.2004.41 · Cited by 234 · cited 2× · see citing works
“requirement for such tools, as it serves as a key prerequisite for the safety of resulting software products [23, 31, 42].”
BackgroundHow to Evaluate Trust in AI-Assisted Decision Making? A Survey of Empirical Methodologies
Vereschak, O., Bailly, G., & Caramiaux, B. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3476068 · Cited by 229 · see citing works
Investigating Explainability of Generative AI for Code through Scenario-based Design
Sun, J., Liao, Q. V., Muller, M., Agarwal, M., Houde, S., Talamadupula, K., & Weisz, J. D. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511119 · Cited by 219 · cited 2× · see citing works
“During the 60-minute retrospective interview sessions, we asked participants about their general experience with AI tools and then asked them to walk through the significant moments they collected during the prior week.”
BackgroundProductivity Assessment of Neural Code Completion
Ziegler, A., Kalliamvakou, E., Li, X. A., Rice, A., Rifkin, D., Simister, S., Sittampalam, G., & Aftandilian, E. (2022) · Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming · doi:10.1145/3520312.3534864 · Cited by 200 · see citing works
How do visual explanations foster end users' appropriate trust in machine learning?
Yang, F., Huang, Z., Scholtz, J., & Arendt, D. L. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377480 · Cited by 200 · cited 1× · see citing works
“For example, since the mechanism of generative AI is more opaque and the outputs are more difficult to anticipate than traditional developer support tools, developers must establish an appropriate level of trust with these AI tools and be cautious about the potential risks [6].”
BackgroundProductivity Assessment of Neural Code Completion
Ziegler, A., Kalliamvakou, E., Simister, S., Sittampalam, G., Li, A., Rice, A., Rifkin, D., & Aftandilian, E. (2022) · arXiv · doi:10.48550/arxiv.2205.06537 · Cited by 200 · see citing works
O’Connor, A. M., Tsafnat, G., Thomas, J., Glasziou, P., Gilbert, S. B., & Hutton, B. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1062-0 · Cited by 167 · cited 1× · see citing works
“On one hand, the lack of trust can prevent users from adopting AI tools in their workflow, even when the performance of the system is superior [10, 49].”
BackgroundDesigning for Responsible Trust in AI Systems: A Communication Perspective
Liao, Q. V., & Sundar, S. S. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533182 · Cited by 165 · cited 10× · see citing works
“For example, P8 thought that “ the aggregated measures of how I’ve used Copilot over time helps me form an image of my relationship with Copilot, which helps me evaluate Copilot’s performance and form informed goals.”
BackgroundMethodInfluentialTaking Flight with Copilot: Early insights and opportunities of AI-powered pair-programming tools
Bird, C., Ford, D., Zimmermann, T., Forsgren, N., Kalliamvakou, E., Lowdermilk, T., & Gazit, I. (2022) · Queue · doi:10.1145/3582083 · Cited by 158 · see citing works
Self-citationEnabling Conversational Interaction with Mobile UI using Large Language Models
Wang, B., Li, G., & Li, Y. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580895 · Cited by 156 · see citing works
In-IDE Code Generation from Natural Language: Promise and Challenges
Xu, F. F., Vasilescu, B., & Neubig, G. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3487569 · Cited by 154 · see citing works
Toward Trustworthy Software Systems
Hasselbring, W., & Reussner, R. (2006) · Computer · doi:10.1109/mc.2006.142 · Cited by 136 · cited 2× · see citing works
“requirement for such tools, as it serves as a key prerequisite for the safety of resulting software products [23, 31, 42].”
BackgroundFriend, Collaborator, Student, Manager
Guzdial, M., Liao, N., Chen, J., Chen, S.-Y., Shah, S., Shah, V., Reno, J. O., Smith, G., & Riedl, M. O. (2019) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300854 · Cited by 134 · cited 5× · see citing works
“At the same time, while prior work on designing user interfaces in AI systems outlined potential principles that could contribute to users’ trust, most studies focused on classification or prediction systems [58] and it is unclear how the principles generalize to generative AI tools, given its novel interaction paradi…”
BackgroundResultInfluentialPerfection 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 · cited 2× · see citing works
“One common approach is to explain AI predictions and decisions using confidence score [58, 69] or visual explanations [65], which could give users means and metrics to assess the performance of AI and make informed trust judgments.”
BackgroundDrozdal, J., Weisz, J., Wang, D., Dass, G., Yao, B., Zhao, C., Muller, M., Ju, L., & Su, H. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377501 · Cited by 119 · cited 1× · see citing works
“Specifically, some emphasize the value of transparency [22] and predictability [19], which helps a user build proper expectations when interacting with AI [35].”
BackgroundReading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Mozannar, H., Bansal, G., Fourney, A., & Horvitz, E. (2022) · arXiv · doi:10.48550/arxiv.2210.14306 · Cited by 114 · cited 1× · see citing works
“As AI code generation tools introduce a brand new interaction paradigm between developers and AI [44, 64], early empirical investigations show that developers struggle to adapt to the new interaction pattern, often having an incomplete mental model of what Copilot can do or not [50] and finding it…”
BackgroundReading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Mozannar, H., Bansal, G., Fourney, A., & Horvitz, E. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641936 · Cited by 114 · see citing works
What Predicts Software Developers’ Productivity?
Murphy-Hill, E., Jaspan, C., Sadowski, C., Shepherd, D., Phillips, M., Winter, C., Knight, A., Smith, E., & Jorde, M. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2900308 · Cited by 100 · cited 1× · see citing works
“Without proper support, developers can find it challenging to form accurate mental models of what AI tools can do or not [50] or determine the quality of specific AI suggestions [5, 48, 55]; thus becoming vulnerable to over-or under-trusting the AI [22, 46].”
BackgroundGender differences and programming environments
Burnett, M., Fleming, S. D., Iqbal, S. T., Venolia, G. D., Rajaram, V., Farooq, U., Grigoreanu, V., & Czerwinski, M. P. (2010) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/1852786.1852824 · Cited by 95 · cited 1× · see citing works
“• How has your perception of trust in the tool changed over time?”
BackgroundSocial influences on secure development tool adoption
Xiao, S., Witschey, J., & Murphy-Hill, E. R. (2014) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2531602.2531722 · Cited by 93 · cited 1× · see citing works
“…what contributes to developers’ trust attitudes in AI code generation tools (RQ1), as well as their challenges in making trust judgments (RQ2), we conducted retrospective interviews with 17 developers who use AI-powered code generation tools in real-life professional or personal settings.”
MethodUser Trust in Intelligent Systems
Holliday, D. D., Wilson, S., & Stumpf, S. (2016) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/2856767.2856811 · Cited by 83 · cited 1× · see citing works
“” User trust can also grow or change over time as users interact with AI systems repeatedly [34] and can be calibrated regarding the context and stake of the task [66].”
BackgroundQuantifying developers' adoption of security tools
Witschey, J., Zielinska, O. A., Welk, A. K., Murphy-Hill, E. R., Mayhorn, C. B., & Zimmermann, T. (2015) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/2786805.2786816 · Cited by 80 · cited 1× · see citing works
“…user trust has long been considered crucial in the design of traditional programming support tools, such as compilers and version control systems [62, 63] to ensure software safety [26, 38], developers’ trust in AI code generation tools needs even more nuanced and careful consideration [6, 17,…”
BackgroundSelf-citationHarnessing Biomedical Literature to Calibrate Clinicians’ Trust in AI Decision Support Systems
Yang, Q., Hao, Y., Quan, K., Yang, S., Zhao, Y., Kuleshov, V., & Wang, F. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581393 · Cited by 75 · cited 1× · see citing works
“A similar approach has been used to explore interface designs for AI-assisted decision-making systems in child welfare [36] and clinical diagnosis [65].”
MethodCapable but Amoral? Comparing AI and Human Expert Collaboration in Ethical Decision Making
Tolmeijer, S., Christen, M., Kandul, S., Kneer, M., & Bernstein, A. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517732 · Cited by 70 · see citing works
Better Together? An Evaluation of AI-Supported Code Translation
Weisz, J. D., Muller, M., Ross, S. I., Martinez, F., Houde, S., Agarwal, M., Talamadupula, K., & Richards, J. T. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511157 · Cited by 69 · cited 1× · see citing works
“As a means to provide support for this complex work, commercial AI-powered code generation tools such as GitHub Copilot [3] and Tabnine [2] have emerged and become a novel service to expert and novice code creators alike.”
MethodA Comprehensive Survey on Program Synthesis With Evolutionary Algorithms
Sobania, D., Schweim, D., & Rothlauf, F. (2022) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2022.3162324 · Cited by 64 · cited 1× · see citing works
“In the context of AI, empirical evidence has also shown that users’ trust is affected by contextual factors such as institution investment, other users’ endorsement, and riskiness of task [33, 61, 69].”
BackgroundAI-Driven Development Is Here: Should You Worry?
Ernst, N. A., & Bavota, G. (2022) · IEEE Software · doi:10.1109/ms.2021.3133805 · Cited by 62 · cited 1× · see citing works
“A review paper highlights that trust in AI is subjective and should be studied as an attitude [56], distinguishing from reliance or compliance, which are often studied as a behavior [54].”
BackgroundMeasuring the Cognitive Load of Software Developers: A Systematic Mapping Study
Gonçales, L. J., Farias, K., da Silva, B., & Fessler, J. (2019) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc.2019.00018 · Cited by 55 · cited 1× · see citing works
“Software engineering is a type of complex and high-demanding information work that often involves high cognitive load and stress [24, 29, 32, 53], and therefore demands high-quality support.”
BackgroundIntegrity-based Explanations for Fostering Appropriate Trust in AI Agents
Mehrotra, S., Jorge, C. C., Jonker, C. M., & Tielman, M. L. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3610578 · Cited by 51 · cited 1× · see citing works
“Our findings in Study 1 reveal that developers tend to trust AI tools when they perceive practical benefits, alignment with their goals, and trustworthy processes.”
BackgroundCheng, R., Wang, R., Zimmermann, T., & Ford, D. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3651990 · Cited by 47 · cited 1× · see citing works
“[15], so that users could further extend their understanding of the capacities and limitations of AI and update their trust.”
BackgroundSelf-citationWhat is it like to program with artificial intelligence?
Sarkar, A., Gordon, A. D., Negreanu, C., Poelitz, C., Ragavan, S. S., & Zorn, B. (2022) · arXiv · doi:10.48550/arxiv.2208.06213 · Cited by 47 · cited 6× · see citing works
“While researchers and software developers are excited about AI-powered code generation tools, these tools also introduce new design challenges in creating responsible and reliable user experiences.”
BackgroundInfluentialDaronnat, S., Azzopardi, L., Halvey, M., & Dubiel, M. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.642201 · Cited by 45 · cited 1× · see citing works
“A related approach is to support the interpretability of model mechanisms [37, 43, 53], increasing the predictability [18, 21] of AI behavior.”
BackgroundKawakami, A., Sivaraman, V., Stapleton, L., Cheng, H.-F., Perer, A., Wu, Z. S., Zhu, H., & Holstein, K. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533556 · Cited by 42 · see citing works
Humans, AI, and Context: Understanding End-Users’ Trust in a Real-World Computer Vision Application
Kim, S. S. Y., Watkins, E. A., Russakovsky, O., Fong, R., & Monroy-Hernández, A. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3593978 · Cited by 37 · cited 5× · see citing works
“Findings from our design probe study (study 2) additionally shed light on opportunities to support users in building and adjusting their trust in AI tools by augmenting existing interfaces with trust affordances.”
BackgroundInfluentialZhang, Y., Suhaimi, N., Yongsatianchot, N., Gaggiano, J. D., Kim, M., Patel, S. A., Sun, Y., Marsella, S., Griffin, J., & Parker, A. G. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501889 · Cited by 37 · cited 4× · see citing works
“…AI assistant tools in software engineering or broader domains [5, 6, 50, 55, 58, 71], we still know little about how their interfaces should be designed to communicate appropriate levels of trustworthiness and help developers form calibrated trust attitudes in AI-powered code generation tools.”
BackgroundMethodInfluentialWendt, E. K., Fridlund, B., & Lidell, E. A.-S. (2004) · Acta Obstetricia Et Gynecologica Scandinavica · doi:10.1111/j.0001-6349.2004.00597.x · Cited by 30 · cited 1× · see citing works
“A similar approach has been applied to study patients’ trust during medical visits [60, 67] and interpersonal trust in business negotiations [45].”
Grounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2022) · arXiv · doi:10.48550/arxiv.2206.15000 · Cited by 23 · cited 9× · see citing works
“One common approach is to explain AI predictions and decisions using confidence score [58, 69] or visual explanations [65], which could give users means and metrics to assess the performance of AI and make informed trust judgments.”
BackgroundMethodInfluentialCrowdsourcing and Evaluating Concept-driven Explanations of Machine Learning Models
Mishra, S., & Rzeszotarski, J. M. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449213 · Cited by 20 · cited 1× · see citing works
“A related approach is to support the interpretability of model mechanisms [37, 43, 53], increasing the predictability [18, 21] of AI behavior.”
BackgroundQuantifying Compliance and Reliance Trust Behaviors to Influence Trust in Human-Automation Teams
Boubin, J. G., Rusnock, C. F., & Bindewald, J. M. (2017) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1541931213601672 · Cited by 19 · cited 1× · see citing works
“The lack of trust can prevent users from adopting AI tools in their workflow, even when the system’s performance is superior [8, 47].”
BackgroundTrust in Collaborative Automation in High Stakes Software Engineering Work: A Case Study at NASA
Widder, D. G., Dabbish, L., Herbsleb, J. D., Holloway, A., & Davidoff, S. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445650 · Cited by 19 · cited 3× · see citing works
“In the context of AI, empirical evidence has also shown that users’ trust is affected by contextual factors such as institution investment, other users’ endorsement, and riskiness of task [33, 61, 69].”
BackgroundCognitive Load Drivers in Large Scale Software Development
Helgesson, D., Engström, E., Runeson, P., & Bjarnason, E. (2019) · International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE) · doi:10.1109/chase.2019.00030 · Cited by 15 · cited 1× · see citing works
“Software engineering is a type of complex and high-demanding information work that often involves high cognitive load and stress [24, 29, 32, 53], and therefore demands high-quality support.”
BackgroundCritical incidents of trust erosion in leadership of head nurses
Gallardo, R. Y., & Süazo, S. V. (2012) · Revista Latino-Americana de Enfermagem · doi:10.1590/s0104-11692012000100019 · Cited by 8 · cited 1× · see citing works
“A similar approach of retrospective interviews and critical incident sampling has been applied to study patients’ trust during medical visits [61, 64] and interpersonal trust in business negotiations [47].”
BackgroundNaikar, N., & Brady, A. (2019) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780198795872.013.10 · Cited by 7 · see citing works
Quality Estimation & Interpretability for Code Translation
Agarwal, M., Talamadupula, K., Houde, S., Martinez, F., Muller, M., Richards, J., Ross, S., & Weisz, J. D. (2020) · arXiv · doi:10.48550/arxiv.2012.07581 · Cited by 3 · cited 1× · see citing works
“found that model confidence scores could be misleading for users’ perception of the quality of model output [6].”
BackgroundDo Users Write More Insecure Code with AI Assistants?
Perry, N., Srivastava, M., Kumar, D., & Boneh, D. (2022) · arXiv · cited 2×
“A related approach is to support the interpretability of model mechanisms [37, 43, 53], increasing the predictability [18, 21] of AI behavior.”
BackgroundMethod
Flagged first, then by citations
Research works printed but not linked: 2
- [40][40] Xiao Ma, Swaroop Mishra, Ariel Liu, Sophie Su, Jilin Chen, Chinmay Kulkarni, Heng-Tze Cheng, Quoc Le, and Ed Chi. 2023. Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses. arXiv preprint arXiv:2312.00763 (2023). - · arXiv
- [51][51] Xinyue Shen, Zeyuan Chen, Michael Backes, and Yang Zhang. 2023. In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT. https://arxiv.org/abs/2304.08979v1 - · arXiv
Cited by
Sorted by citations
Software Testing With Large Language Models: Survey, Landscape, and Vision
Wang, J., Huang, Y., Chen, C., Liu, Z., Wang, S., & Wang, Q. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3368208 · Cited by 573 · see citing works
“• The paper focuses on evaluating the performance of LLM-enabled tools, e.g., evaluating the code quality of the code generation tool Copilot [127], [128], [129].”
Artificial intelligence for literature reviews: opportunities and challenges
Bolaños, F., Salatino, A., Osborne, F., & Motta, E. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10902-3 · Cited by 246 · see citing works
Navigating the Complexity of Generative AI Adoption in Software Engineering
Russo, D. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3652154 · Cited by 217 · see citing works
“Our research of the literature revealed only three papers that even mention these tools, and solely within the context of related work or discussion sections [16, 42, 114].”
BackgroundIronies of Generative AI: Understanding and Mitigating Productivity Loss in Human-AI Interaction
Simkute, A., Tankelevitch, L., Kewenig, V., Scott, A. E., Sellen, A., & Rintel, S. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2405782 · Cited by 89 · see citing works
“…highlight prompt changes and the resulting output changes (Zamfirescu-Pereira et al., 2023), use explain-ability features indicating factors that influenced the output (Bauer et al., 2023), or use an analytic dashboard that shows statistics of AI tools’ performance changes (Wang et al., 2024).”
Influential"I look at it as the king of knowledge": How Blind People Use and Understand Generative AI Tools
Adnin, R., & Das, M. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675631 · Cited by 73 · see citing works
“Nowadays, people are incorporating GenAI tools (e.g., ChatGPT [73], Google Gemini [33], Microsoft Copilot [65], and Claude [5]) into a wide variety of domains, including education [36, 62, 83], programming [16, 54, 92], communication [14], and content creation [45, 56].”
BackgroundMethodKuhail, M. A., Mathew, S. S., Khalil, A., Berengueres, J., & Shah, S. J. H. (2024) · Science of Computer Programming · doi:10.1016/j.scico.2024.103111 · Cited by 68 · see citing works
Copiloting the future: How generative AI transforms Software Engineering
Banh, L., Holldack, F., & Strobel, G. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107751 · Cited by 66 · see citing works
Bikanga Ada, M. (2024) · Education Sciences · doi:10.3390/educsci14101106 · Cited by 40 · see citing works
Zhou, X., Liang, P., Zhang, B., Li, Z., Ahmad, A., Shahin, M., & Waseem, M. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2024.112204 · Cited by 30 · see citing works
Validating AI-Generated Code with Live Programming
Ferdowsi, K., Huang, R. L., James, M. B., Polikarpova, N., & Lerner, S. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642495 · Cited by 27 · see citing works
The Impact of Generative AI Coding Assistants on Developers Who Are Visually Impaired
Flores-Saviaga, C., Hanrahan, B. V., Imteyaz, K., Clarke, S., & Savage, S. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714008 · Cited by 24 · see citing works
“Building on Gajos et al.’s adaptive interfaces concept [31], our fndings suggest that AI-assisted coding environments could ben-eft from adaptive features.”
Generative AI: Current Status and Future Directions
Leong, L.-Y., Hew, T., Ooi, K., Tan, G., & Koohang, A. (2025) · Journal of Computational Information Systems · doi:10.1080/08874417.2025.2482571 · Cited by 18 · see citing works
Students' Use of GitHub Copilot for Working with Large Code Bases
Shah, A., Chernova, A., Tomson, E., Porter, L., Griswold, W. G., & Soosai Raj, A. G. (2025) · Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1 · doi:10.1145/3641554.3701800 · Cited by 19 · see citing works
What Guides Our Choices? Modeling Developers' Trust and Behavioral Intentions Towards Genai
Choudhuri, R., Trinkenreich, B., Pandita, R., Kalliamvakou, E., Steinmacher, I., Gerosa, M. A., Sanchez, C. A., & Sarma, A. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00087 · Cited by 22 · see citing works
Generative AI Uses and Risks for Knowledge Workers in a Science Organization
Wagman, K. B., Dearing, M. T., & Chetty, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713827 · Cited by 16 · see citing works
“Thus, researchers are considering how to design for the appropriate level of trust users should put in a system [58].”
Human-AI experience in integrated development environments: a systematic literature review
Sergeyuk, A., Zakharov, I., Koshchenko, E., & Izadi, M. (2026) · Empirical Software Engineering · doi:10.1007/s10664-025-10793-0 · Cited by 26 · see citing works
“– Explainability & Transparency : Tools should provide context-aware explanations and highlight uncertain AI-generated code (Vasconcelos et al., 2024; Yan et al., 2024; Sun et al., 2022; Wang et al., 2024) to improve user trust.”
BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks
Cheng, R., Barik, T., Leung, A., Hohman, F., & Nichols, J. W. (2024) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc60511.2024.00012 · Cited by 15 · see citing works
“Users may also overrely and overtrust code generated by LLMs, overlooking potential issues and alternative solutions [5], [6].”
Self-citationHow Much Does AI Impact Development Speed? an Enterprise-Based Randomized Controlled Trial
Paradis, E., Grey, K., Madison, Q., Nam, D., Macvean, A., Meimand, V., Zhang, N., Ferrari-Church, B., & Chandra, S. (2025) · 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip66354.2025.00060 · Cited by 20 · see citing works
“Recent work has explored the potential of these tools to assist students and novice programmers [8], [23], [24], as well as program-mers’ perceptions of [25], [26], [27] and trust in [28], [29], [30] AI tools.”
Building Your Own Product Copilot: Challenges, Opportunities, and Needs
Parnin, C., Soares, G., Pandita, R., Gulwani, S., Rich, J., & Henley, A. Z. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00039 · Cited by 32 · see citing works
Perera, M., Ananthanarayan, S., Goncu, C., & Marriott, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713634 · Cited by 14 · see citing works
“GenAI tools, such as ChatGPT [ 88], Google Gemini (formerly Bard) [48], and Copilot [79], have gained immense popularity and have been incorporated into various domains, including work [27, 40], education [8, 75], programming [39, 116], content creation [54], and accessibility [63, 111].”
Basha, M., & Rodríguez-Pérez, G. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107804 · Cited by 14 · see citing works
Challenges and Paths Towards AI for Software EngineeringPreprint
Gu, A., Jain, N., Li, W., Shetty, M., Shao, Y., Li, Z., Yang, D., Ellis, K., Sen, K., & Solar-Lezama, A. (2025) · Qeios · doi:10.32388/vv1661 · Cited by 24 · see citing works
Exploring Student-AI Interactions in Vibe Coding
Geng, F., Shah, A., Li, H., Mulla, N., Swanson, S., Raj, G. S., Zingaro, D., & Porter, L. (2026) · Australasian Computing Education Conference · doi:10.1145/3786228.3786236 · Cited by 9 · see citing works
Understanding and Designing for Trust in AI-Powered Developer Tooling
Murillo, A., Elizondo, A., D’Angelo, S., Brown, A., Kumar, U., Madison, Q., & Macvean, A. (2024) · IEEE Software · doi:10.1109/ms.2024.3439108 · Cited by 8 · see citing works
A Transformer-Based Approach for Smart Invocation of Automatic Code Completion
de Moor, A., van Deursen, A., & Izadi, M. (2024) · Proceedings of the 1st ACM International Conference on AI-Powered Software · doi:10.1145/3664646.3664760 · Cited by 7 · see citing works
“Since its inception, several user studies and surveys [2, 24, 31, 33, 34, 42, 44, 49] have been performed on GitHub Copilot 4 .”
BackgroundKudriavtseva, A., Hotak, N. A., & Gadyatskaya, O. (2025) · Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing · doi:10.1145/3672608.3707778 · Cited by 9 · see citing works
“Wang et al. [47] discovered that developers trust AI tools as these increase productivity and improve code quality, but some developers prefer to use AI tools only for simple tasks such as writing unit tests.”
Redefining the Programmer: Human-AI Collaboration, LLMs, and Security in Modern Software Engineering
Cruz, E. D. L., Le, H., Meduri, K., Nadella, G. S., & Gonaygunta, H. (2025) · Computers, Materials & Continua · doi:10.32604/cmc.2025.068137 · Cited by 9 · see citing works
“This issue resides in software security, which is critical in areas such as healthcare, finance, and defense, where even minor oversights can lead to data breaches or system compromise [12].”
Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications
Sabouri, S., Eibl, P., Zhou, X.-Y., Ziyadi, M., Medvidović, N., Lindemann, L., & Chattopadhyay, S. (2025) · International Conference on Software Engineering · doi:10.1109/icse55347.2025.00199 · Cited by 17 · see citing works
“The importance of supporting the underlying process is imminent from the increasing number of very recent publications looking into the dynamics of what influences developer trust [12], [13].”
Evolution of Programmers' Trust in Generative AI Programming Assistants
Shah, A., Rexin, T., Tomson, E., Griswold, W. G., Porter, L., & Raj, A. G. S. (2025) · Koli Calling International Conference on Computing Education Research · doi:10.1145/3769994.3770029 · Cited by 7 · see citing works
“We observe that there are three common ways to understand trust in the aforementioned literature: 1) survey instruments [3, 31, 36], 2) interviews or written free-responses from developers [3, 7, 13, 19, 37], and 3) acceptance rate of AI-generated code [11, 29, 32].”
InfluentialLau, S., & Guo, P. J. (2025) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc65237.2025.00041 · Cited by 6 · see citing works
“A nearby cluster of related work is empirical studies of the user experience of specific AI coding assistants, done via controlled lab studies, user interviews, chat log analysis, or online surveys [19]–[24].”
The Transformative Influence of LLMs on Software Development & Developer Productivity
Jalil, S. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166110 · Cited by 6 · see citing works
“The recommendations provided by these tools can occasionally mislead the developer, presenting multiple challenges, including issues with execution history, tool customization, and fine-tuning [32], [41].”
InfluentialMapping the Trust Terrain: LLMs in Software Engineering - Insights and Perspectives
Khati, D., Liu, Y., Palacio, D. N., Zhang, Y., & Poshyvanyk, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771282 · Cited by 5 · see citing works
Transforming the self: Individual-level changes arising from collaboration with generative AI
Nandagopal, S. (2025) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2025.100232 · Cited by 9 · see citing works
AI Pair Programming Acceptance: A Value-Based Approach with AHP Analysis
Çaldağ, M. T. (2024) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit62066.2024.10708135 · Cited by 4 · see citing works
Jo, J., Zhang, H., Cai, J., & Goyal, N. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732077 · Cited by 7 · see citing works
Comparative Analysis of ChatGPT, DeepSeek, and Gemini for Automated Code Generation
Shahzad, K., & Iqbal, S. (2025) · International Conference on Engineering of Modern Electric Systems · doi:10.1109/emes65692.2025.11045587 · Cited by 5 · see citing works
“Conversely, critics caution that AI-generated code may be less robust, secure, and maintainable, especially in mission-critical applications [5].”
Spark: Real-Time Monitoring of Multi-Faceted Programming Exercises
Yang, Y., Zhang, G., Oney, S., & Wang, A. Y. (2025) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc65237.2025.00018 · Cited by 4 · see citing works
“In the context of AI-generated code, research highlights the importance of building trust through runtime feedback [45], with visualizing intermediate values shown to help validate AI outputs [46].”
Architecting open, accountable, and trustworthy AI-IDEs
Contreras, A., Guerra, E., & de Lara, J. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00608-x · Cited by 4 · see citing works
Chen, N., Qiu, L. K., Wang, A. Z., Wang, Z., & Yang, Y. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790726 · Cited by 8 · see citing works
“At the same time, issues such as buggy outputs, limited transparency, and abstraction gaps between developers and underlying models continue to hinder effective use of these tools in practice [28, 54, 92].”
Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding
Chou, Y.-H., Jiang, B., Chen, Y. W., Weng, M., Jackson, V., Zimmermann, T., & Jones, J. A. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797105 · Cited by 3 · see citing works
Self-citationEmpirical Evidence on Conversational Control of GUI in Semantic Automation
Weidele, D. K. I., Martino, M., Valente, A. N., Rossiello, G., Strobelt, H., Franke, L., Alvero, K., Misko, S., Auer, R., Bagchi, S., et al. (2024) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3640543.3645172 · Cited by 3 · see citing works
“These encompass providing clear feedback on AI’s performance, allowing users to modify AI preferences as needed, and ensuring a clear understanding of the underlying processes of AI, all aiming to build more vital trust in these systems [51].”
BackgroundEnsemble Balanced Nested Dichotomy Fuzzy Models for Software Requirement Risk Prediction
Kumar, G., Imam, A. A., Basri, S. B., Hashim, A. S., Naim, A. G., Capretz, L. F., Balogun, A. O., & Mamman, H. (2024) · IEEE Access · doi:10.1109/access.2024.3473942 · Cited by 3 · see citing works
“GitHub Copilot can autocomplete code, generate entire functions, and suggest best practices, significantly speeding up the coding process [5].”
MethodCracking CodeWhisperer: Analyzing Developers’ Interactions and Patterns During Programming Tasks
Javahar, J., Budhrani, T., Basha, M., de Souza, R. B. C., Beschastnikh, I., & Rodríguez-Pérez, G. (2025) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc65237.2025.00051 · Cited by 2 · see citing works
Семеновна, Р. А., & Воронин, А. Н. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2580550 · Cited by 2 · see citing works
“…� Software Development: Developers exhibited context-dependent trust, relying on AI for low-stakes tasks but remaining cautious in high-stakes scenarios (Wang et al., 2024); � Information Retrieval: Trust was built through direct responses, contingent interaction, and high speed (Jung et al.,…”
InfluentialGeoPandas-AI: A Smart Class Bringing LLM as Stateful AI Code Assistant
Merten, G., Dejaegere, G., & Sakr, M. A. (2025) · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS) · doi:10.1145/3748636.3762765 · Cited by 2 · see citing works
Ties of Trust: a bowtie model to uncover trustor-trustee relationships in LLMs
Paraschou, E., Michali, M., Yfantidou, S., Karamanidis, S., Kalogeros, S. R., & Vakali, A. I. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732115 · Cited by 2 · see citing works
“The sample size aligns with similar notable studies in the community employing on-site interactions and individual activities [10, 17, 34, 48, 65, 67].”
CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
Basha, M., Ribeiro, A. M., Javahar, J., de Souza, C. R. B., & Rodríguez-Pérez, G. (2025) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme64153.2025.00110 · Cited by 2 · see citing works
“More studies about these tools rely on surveys, video recordings, and inter-views [13], [14], [15], [16], [17] (with two exceptions [11], [18]).”
Artificial Intelligence Integration in Programming Education: Implications for Pedagogy and Practice
Rajendran, V., & Ramasamy, R. K. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-7794-5_16 · Cited by 1 · see citing works
Vaishampayan, S., & Brown, C. (2025) · International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE) · doi:10.1109/chase66643.2025.00018 · Cited by 1 · see citing works
“Previous AI-assisted code systems mainly focus on one construct at a time— for instance, code generation with GitHub Copilot [38].”
Symbio Coding: An Educational Testbed for AI Agent Simulation as Software Development Team Member
Misnevs, B., Savrasovs, M., & Spiridovska, N. (2025) · International Conference Innovation Engineering and Technology · doi:10.1109/iciet66371.2025.11045965 · Cited by 1 · see citing works
"Maybe We Need Some More Examples:" Individual and Team Drivers of Developer GenAI Tool Use
Miller, C., Choudhuri, R., Ulloa, M., Haniyur, S., DeLine, R. A., Storey, M.-A., Murphy-Hill, E. R., Bird, C., & Butler, J. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3773155 · Cited by 7 · see citing works
On the Need to Rethink Trust in AI Assistants for Software Development: A Critical Review
Baltes, S., Speith, T., Chiteri, B., Mohsenimofidi, S., Chakraborty, S., & Buschek, D. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3659804 · Cited by 5 · see citing works
“…[175] [91] None SE-CR [4], [22], [78], [111], [165] None None None PH+PS [30], [38], [56], [62], [86], [96], [110], [117], [118], [124], [133], [161], [164], [169] None None None times referred to as “ postadoption ”, where aspects such as predictability and helpfulness of a tool [121] play an…”
CodeVoyager: Integrating Interactive Visual Aids with LLMs for Code Comprehension
Kim, Y., Jang, K., Song, H., Shin, M., & Suh, B. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789057 · Cited by 1 · see citing works
When Help Hurts: Verification Load and Fatigue with AI Coding Assistants
Fan, G. F., Liu, D., Pan, L., & Zhang, R. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791176 · Cited by 2 · see citing works
Jang, Y., Sakashita, M., Niinuma, K., & Gupta, A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791260 · Cited by 1 · see citing works
“Experts may underuse AI due to skepticism, missing opportunities to correct mistakes [48], while even established trust remains fragile and can be undermined by a single error [67].”
Cherner, T. S., & Donnelly, M. (2026) · Education Sciences · doi:10.3390/educsci16050706 · Cited by 2 · see citing works
Alhubaishy, A. A. (2026) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi68585.2026.11539834 · Cited by 1 · see citing works
“Trust is a key factor in AI adoption, with studies showing that developers assess it based on the AI’s ability, integrity, and benevolence [33], [34].”
Dhanorkar, S., Passi, S., & Vorvoreanu, M. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812402 · Cited by 3 · see citing works
“…out, there is a pressing need for more empirical, human-centered research to examine how users navigate such tradeoffs when working with agentic systems in practice, likely “compensat[ing] for unmet” needs [133] through oft-invisible situated actions and intuitions [11, 20, 39, 69, 94, 133, 136].”
InfluentialHow Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior
Wu, Y., Li, Z. S., Stolee, K. T., & Xu, B. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3808120 · Cited by 1 · see citing works
How do Copilot Suggestions Impact Developers' Frustration and Productivity?
Guglielmi, E., Arnoudova, V., Bavota, G., Oliveto, R., & Scalabrino, S. (2025) · arXiv · doi:10.48550/arxiv.2504.06808 · Cited by 1 · see citing works
“Wang et al. [34] report that frustration is caused both by insufficient help and invasive and premature suggestions not aligned with developers’ intentions.”
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
La Malfa, G., Meegahapola, L., Bogucka, E., Zhang, J. M., Luck, M., Black, E., & Quercia, D. (2026) · arXiv · doi:10.48550/arxiv.2608.08601
“AI augmentation, where the agent assists rather than re-places the human, is often treated as the more responsible deployment choice (Wang et al. 2024a; Shao et al. 2025b).”
It’s Organic: Software Testing of Emerging Domains (Keynote)
Cohen, M. B. (2024) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3663529.3674720
“And we are now using large language models as programming assistants [11].”
Pimenov, A., & Kovalchuk, S. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78459-0_25
Ceccucci, W., Peslak, A. R., & Jones, K. G. (2025) · Journal of Information Systems Applied Research and Analytics · doi:10.62273/oemc9700
Democratisation of Generative Artificial Intelligence
Paluszak, J., & Oliynychuk, O. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83708-432-620251005
Towards Just-In-Time, Inclusive Clone Refactoring
Roy, P. R. (2025) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme64153.2025.00099
Ju, M., Jun, H. K., Kim, T., & Kim, H.-J. (2025) · IEEE Pacific Rim International Symposium on Dependable Computing (PRDC) · doi:10.1109/prdc67299.2025.00026
Evaluating AI-Generated C# Code in Computing Education: Implications for Academic Integrity
Adegbite, A. A., & Kotzé, E. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12457-9_8
Who Wrote This Code? Investigating Human and AI Programming Patterns
Nitika, & Narwal, R. (2025) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip68302.2025.11346257
Lumen: Developer Agency Through Transparent Context Control in AI-Assisted Programming
Goel, N., & Melo, G. (2025) · IEEE International Conference on Collaborative Advances in Software and Computing (CASCON) · doi:10.1109/cascon66301.2025.00024
“This opacity creates anxiety, particularly for production systems where a missed dependency or ignored security constraint can have serious consequences [13], [14].”
BugBlaze: An Explainable Framework for Detecting Latent Defect Ignitions in Software Systems
Yalamancheli, H., Shaik, N., Amanmadov, N., Abdullayev, T., & Brahmandam, B. A. (2025) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon67450.2025.11381085
“Opaque outputs reduce confidence, while clear explanations and work-flow integration improve adoption; effective examples reduce cognitive load [3].”
What You See Is Not Always What You Get: Evaluating GPT’s Comprehension of Source Code
Wen, J., Zhu, B., & Chen, H. (2025) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec66846.2025.00045
Everyday Practitioner Experiences of AI-First Policies Adopted by U.S. Big Tech Companies
Jeong, K.-J., Zhang, Z.-T., Dong, J.-X., Chung, A., & Shih, P. C. (2026) · International Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791271 · Cited by 1 · see citing works
“Teams in the same organization validate GenAI outputs with widely varying rigor [82].”
Ye, Z., Liang, X., & Cheng, P. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6604907
CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMsPreprint
Rodríguez-Pérez, G., & Basha, M. (2025) · OSF Preprints (OSF Preprints)
Forecasting Developer Environments with GenAI: A Research Perspective
Kula, R. G., Treude, C., Hu, X., Baltes, S., Barr, E. T., Blincoe, K., Calefato, F., Chen, J., Cheong, M., Fan, Y., et al. (2026) · IDE@ICSE · doi:10.1145/3786151.3788604
“Transparency and trust are essential: developers need to understand how the system arrives at its recommendations or predictions, which in turn fosters confidence in automated decisions [5, 50].”
Zubair, M. A., Bouchelligua, W., Danish, S., Ahmad, S., & Ksibi, A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115708
Zeng, L., Kuang, E., & Zhao, J. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3813023
“Prior work highlights the importance of making control options explicit and supporting based on context [13, 69] In the context of constraint-driven presentation authoring, such a balance is particularly important because presenters are making nuanced tradeoffs across contextual constraints.”
Do You Trust the Process?: Trust-Contingent Reinforcement Learning for Resource Allocation
Balepur, N., Subramonian, K., & Sundaram, H. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812274
A comprehensive analysis of security risks and productivity impacts of AI-generated code
Zardari, S., Osama, M., Ammar, S. M., Reshamwala, R. I., & Siddiqui, A. (2026) · AI and Ethics · doi:10.1007/s43681-026-01203-2
Beyond Code: Empirical Insights into How Team Dynamics Influence OSS Project Selection
Nirmani, S., Khalajzadeh, H., Shahin, M., & Liu, X. (2026) · International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE) · doi:10.1145/3794860.3794901
Gardella, N., Bolton, M. L., & Riggs, S. L. (2026) · Human Factors The Journal of the Human Factors and Ergonomics Society · doi:10.1177/00187208261467254
Grasping AI Reliance in Program Comprehension and Coding through the AIRELI Persona Taxonomy
Alakmeh, T., Anderson, N. B., Jackson, V., Pereira, G. V., Akırmak, Ü., Estey, A., Prikladnicki, R., van der Hoek, A., Storey, M., & Fritz, T. (2026) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1145/3794763.3794804
“Across these threats, researchers emphasize calibration of trust as a mediating factor that shapes whether outputs are scrutinized, tested, and adapted or accepted with minimal evaluation [8, 41, 46].”
Pu, S., Liu, Y., & Wu, X. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0291-1_26
From Design to Code: Exploring LLM-Supported Workflows in Figma Dev Mode
Rajpal, S., & Riener, A. (2026) · Mensch und Computer (MuC) · doi:10.1145/3820253.3820266
The Developer as Curator: A Canvas for Coding Agent Context
Böhme, L., Beckmann, T., Perscheid, M., & Hirschfeld, R. (2026) · ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward!) · doi:10.1145/3840586.3843212
Ugochukwu, P., Kazeem, A., Bland, A., Black, B., & Strawderman, L. J. (2026) · Theoretical and Applied Ergonomics · doi:10.3390/tae2040024
“Wang et al. [22] found that developers’ trust in AI code generation tools was largely determined by the accuracy and contextual fit of suggestions, rather than transparency mechanisms such as explanation panels or confidence scores.”
Individual-Scale Governance: Why Speed Increases the Need for Structure in Vibe Coding Workflows
Vance, B., & Getto, G. (2026) · IEEE International Professional Communication Conference (ProComm) · doi:10.1109/procomm69759.2026.00043
Tanantong, T., Kasetruengphol, C., Chemkomnerd, N., & Kraiwanit, T. (2026) · Publications · doi:10.3390/publications14040071
Hinderks, A., Thomaschewski, J., & Schön, E.-M. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-39205-3_8
Plausible Is Not Enough: Trust and Evidence in AI-Authored Pull Request Review
Rahman, M. S., Alam, K., Roy, B., & Roy, C. K. (2026) · arXiv · doi:10.48550/arxiv.2610.21144
- Authors
- Wang, R., Cheng, R., Ford, D., & Zimmermann, T.
- Affiliations
- University of Washington (US)
- Microsoft (United States) (US)
- Venue
- The 2024 ACM Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2024-06-03
- Pages
- 1475-1493
- OpenAlex
- W4399361983
- Cited by
- 87
- References
- 62
- Citations by year
- 2026: 32 · 2025: 38 · 2024: 17
- FWCI
- 33.13
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Microsoft Research
- University of Washington
- 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
- trust in AI, developer trust, trust evaluation, situational trust, trust indicators, usage statistics, control mechanisms
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
