Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents—which can automatically write files and run code—still rely on static benchmarks. We present the first controlled study of developer interactions with coding agents, characterizing how more autonomous AI tools affect productivity and experience. We evaluate two leading copilot and agentic coding assistants, recruiting participants who regularly use the former. Our results show agents can assist developers in ways that surpass copilots (e.g., completing tasks humans may not have accomplished) and reduce the effort required to finish tasks. Yet challenges remain for broader adoption, including ensuring users adequately understand agent behaviors. Our findings reveal how workflows shift with coding agents and how interactions differ from copilots, motivating recommendations for researchers and highlighting challenges in adopting agentic systems.

Current in-IDE AI coding tools typically rely on time-consuming manual prompting and context management, whereas proactive alternatives that anticipate developer needs without explicit invocation remain underexplored. Understanding when humans are receptive to such proactive AI assistance during their daily work remains an open question in human-AI interaction research. We address this gap through a field study of proactive AI assistance in professional developer workflows. We present a five-day in-the-wild study with 15 developers who interacted with a proactive feature of an AI assistant integrated into a production-grade IDE that offers code quality suggestions based on in-IDE developer activity. We examined 229 AI interventions across 5,732 interaction points to understand how proactive suggestions are received across workflow stages, how developers experience them, and their perceived impact. Our findings reveal systematic patterns in human receptivity to proactive suggestions: interventions at workflow boundaries (e.g., post-commit) achieved 52% engagement rates, while mid-task interventions (e.g., on declined edit) were dismissed 62% of the time. Notably, well-timed proactive suggestions required significantly less interpretation time than reactive suggestions (45.4s versus 101.4s, W = 109.00, r = 0.533, p = 0.0016), indicating enhanced cognitive alignment. This study provides actionable implications for designing proactive coding assistants, including how to time interventions, align them with developer context, and strike a balance between AI agency and user control in production IDEs.

Individual human decision-makers may benefit from different forms of support to improve decision outcomes, but when will each form of support yield better outcomes? In this work, we posit that personalizing access to decision support tools can be an effective mechanism for instantiating the appropriate use of AI assistance. Specifically, we propose the general problem of learning a decision support policy that, for a given input, chooses which form of support to provide to decision-makers for whom we initially have no prior information. We develop Modiste, an interactive tool to learn personalized decision support policies. Modiste leverages stochastic contextual bandit techniques to personalize a decision support policy for each decision-maker. In our computational experiments, we characterize the expertise profiles of decision-makers for whom personalized policies will outperform offline policies, including population-wide baselines. Our experiments include realistic forms of support (e.g., expert consensus and predictions from a large language model) on vision and language tasks. Our human subject experiments add nuance to and bolster our computational experiments, demonstrating the practical utility of personalized policies when real users benefit from accessing support across tasks.

Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no existing solution. We introduce Copilot Arena, a platform to collect user preferences through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy to reduce experienced latency, and a prompting scheme to enable code completion functionality. Copilot Arena has served over 4.5 million suggestions from 10 models and collected over 11k pairwise judgements. Our results highlight the importance of model evaluations in integrated settings. We find that model rankings from Copilot Arena differ from those of existing evaluations, which we attribute to the unique distribution of data and tasks contained in Copilot Arena. We also identify novel insights into human preferences on code such as an observed consistency in user preference across programming languages yet significant variation in preference due to task category. We open-source Copilot Arena and release data to enable human-centric evaluations and improve understanding of coding assistants.

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, generally leading to overestimation of methods' real-world utility. In this work, we seek to address this by conducting a study that evaluates post-hoc explainable ML methods in a setting consistent with the application context and provide a template for future evaluation studies. We modify and improve a prior study on e-commerce fraud detection by relaxing the original work's simplifying assumptions that departed from the deployment context. Our study finds no evidence for the utility of the tested explainable ML methods in the context, which is a drastically different conclusion from the earlier work. This highlights how seemingly trivial experimental design choices can yield misleading conclusions about method utility. In addition, our work carries lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended application context but also developing methods tailored to specific applications, moving beyond general-purpose explainable ML methods.

Abstract One widely cited barrier to the adoption of LLMs as proxies for humans in subjective tasks is their sensitivity to prompt wording—but interestingly, humans also display sensitivities to instruction changes in the form of response biases. We investigate the extent to which LLMs reflect human response biases, if at all. We look to survey design, where human response biases caused by changes in the wordings of “prompts” have been extensively explored in social psychology literature. Drawing from these works, we design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior, particularly in models that have undergone RLHF. Furthermore, even if a model shows a significant change in the same direction as humans, we find that they are sensitive to perturbations that do not elicit significant changes in humans. These results highlight the pitfalls of using LLMs as human proxies, and underscore the need for finer-grained characterizations of model behavior.1

Share on Are Model Explanations Useful in Practice? Rethinking How to Support Human-ML Interactions Author: Valerie Chen Machine Learning, Carnegie Mellon University, USA Machine Learning, Carnegie Mellon University, USA 0009-0007-2783-0265View Profile Authors Info & Claims AIES '23: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and SocietyAugust 2023Pages 942–944https://doi.org/10.1145/3600211.3604726Published:29 August 2023Publication History 0citation56DownloadsMetricsTotal Citations0Total Downloads56Last 12 Months56Last 6 weeks9 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

AI explanations are often mentioned as a way to improve human-AI decision-making, but empirical studies have not found consistent evidence of explanations' effectiveness and, on the contrary, suggest that they can increase overreliance when the AI system is wrong. While many factors may affect reliance on AI support, one important factor is how decision-makers reconcile their own intuition---beliefs or heuristics, based on prior knowledge, experience, or pattern recognition, used to make judgments---with the information provided by the AI system to determine when to override AI predictions. We conduct a think-aloud, mixed-methods study with two explanation types (feature- and example-based) for two prediction tasks to explore how decision-makers' intuition affects their use of AI predictions and explanations, and ultimately their choice of when to rely on AI. Our results identify three types of intuition involved in reasoning about AI predictions and explanations: intuition about the task outcome, features, and AI limitations. Building on these, we summarize three observed pathways for decision-makers to apply their own intuition and override AI predictions. We use these pathways to explain why (1) the feature-based explanations we used did not improve participants' decision outcomes and increased their overreliance on AI, and (2) the example-based explanations we used improved decision-makers' performance over feature-based explanations and helped achieve complementary human-AI performance. Overall, our work identifies directions for further development of AI decision-support systems and explanation methods that help decision-makers effectively apply their intuition to achieve appropriate reliance on AI.

A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use cases. However, running user studies is challenging and costly, and consequently each study typically only evaluates a limited number of different settings, e.g., studies often only evaluate a few arbitrarily selected model explanation methods. To address these challenges and aid user study design, we introduce Simulated Evaluations (SimEvals). SimEvals involve training algorithmic agents that take as input the information content (such as model explanations) that would be presented to the user, to predict answers to the use case of interest. The algorithmic agent's test set accuracy provides a measure of the predictiveness of the information content for the downstream use case. We run a comprehensive evaluation on three real-world use cases (forward simulation, model debugging, and counterfactual reasoning) to demonstrate that SimEvals can effectively identify which explanation methods will help humans for each use case. These results provide evidence that \simevals{} can be used to efficiently screen an important set of user study design decisions, e.g., selecting which explanations should be presented to the user, before running a potentially costly user study.

When subjected to automated decision-making, decision subjects may strategically modify their observable features in ways they believe will maximize their chances of receiving a favorable decision. In many practical situations, the underlying assessment rule is deliberately kept secret to avoid gaming and maintain competitive advantage. The resulting opacity forces the decision subjects to rely on incomplete information when making strategic feature modifications. We capture such settings as a game of Bayesian persuasion, in which the decision maker offers a form of recourse to the decision subject by providing them with an action recommendation (or signal) to incentivize them to modify their features in desirable ways. We show that when using persuasion, the decision maker and decision subject are never worse off in expectation, while the decision maker can be significantly better off. While the decision maker’s problem of finding the optimal Bayesian incentive compatible (BIC) signaling policy takes the form of optimization over infinitely many variables, we show that this optimization can be cast as a linear program over finitely-many regions of the space of possible assessment rules. While this reformulation simplifies the problem dramatically, solving the linear program requires reasoning about exponentially-many variables, even in relatively simple cases. Motivated by this observation, we provide a polynomial-time approximation scheme that recovers a near-optimal signaling policy. Finally, our numerical simulations on semi-synthetic data empirically demonstrate the benefits of using persuasion in the algorithmic recourse setting.

Deep-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. This ability to determine the novelty of a new input with respect to a trained model is critical for such systems because novel inputs due to changes in the environment, adversarial attacks, or even unintentional noise can potentially lead to erroneous, perhaps life-threatening decisions. This paper proposes a learning framework that leverages information learned by the prediction model in a task-aware manner to detect novel scenarios. We use network saliency to provide the learning architecture with knowledge of the input areas that are most relevant to the decision-making and learn an association between the saliency map and the predicted output to determine the novelty of the input. We demonstrate the efficacy of this method through experiments on real-world driving datasets as well as through driving scenarios in our in-house indoor driving environment where the novel image can be sampled from another similar driving dataset with similar features or from adversarial attacked images from the training dataset. We find that our method is able to systematically detect novel inputs and quantify the deviation from the target prediction through this task-aware approach.