arXiv subjects

Jenny T. Liang

Publications and source records attributed to Jenny T. Liang.

17 recordsLinked to original sources

arXiv2026

Learning from 53.6K Real-World Developer Edits of AI-Generated Code

Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant. Manual code edits provide more realistic and granular information on editing behavior than Git commits, which only contain final successful code snippets. Yet, due to a lack of high-quality, realistic code editing data, LLMs are mostly trained on publicly available Git data (e.g., commits). To address this gap, we introduce DECODE (Developer Edits of Code Dataset), a dataset of 53.6K real-world in-IDE code edits of AI-generated code in Python, TypeScript, and JavaScript, sourced from 1K+ developers. First, we demonstrate the utility of DECODE for data analysis, obtaining insights on when, why, and how AI-generated code is edited. We find that most edits occur within the first 15 minutes after accepting an AI completion, resulting in the removal of AI completions in 31% of edit trajectories. Second, we use DECODE to benchmark the ability of LLMs to predict code edits. We find that finetuning on DECODE enables open-source 3B models to perform code edit prediction tasks significantly better than frontier LLMs. We then discuss implications of this work, emphasizing the necessity of developer-centric machine learning approaches for future AI programming assistants.

cs.SE↗

arXiv2026

Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes

Computer use agents (or "agents") are generative AI that automates actions within user interfaces from user commands. Current research focuses on training and evaluating the underlying models, leaving these agents' user experience (UX) understudied. We conducted two studies to understand the design space of agent UX (RQ1) and the support required to prototype it (RQ2). First, we develop a taxonomy of design considerations for agent UX, comprising 21 subcategories of UX considerations. Then, through a requirements elicitation study with 12 participants---including six agent experts---we identify five Activities and six Desired Capabilities needed in tools prototyping agent UX. Informed by these results, we created AgentUXlab, a design probe that enables developers to design agents with different UX approaches for a website and evaluate those experiences by executing prototypes in a browser. From a user study with 14 participants, we elucidate tooling insights and derive design implications for agent UX prototyping tools.

cs.HC↗

arXiv2026

When Should AI Read the Room? Public Perceptions of Social Intelligence in AI Agents

AI researchers have been advancing socially intelligent AI agents (Social-AI) across embodiments, from chatbots to physical robots. As Social-AI is increasingly deployed in everyday settings, decisions about the roles these agents should play will depend on how laypeople perceive them. However, public perceptions of social intelligence in AI agents and the acceptability of these agents remain largely understudied. We present a mixed-methods survey of adults in the United States (N=200) that examines social intelligence as a perceived construct in AI agents. Our survey investigates the extent to which participants believe current AI agents have social intelligence, abilities of agents that participants associate with social intelligence, contextual factors influencing participant acceptance of Social-AI agents, and concerns participants hold about these technologies. Participants widely reported having already encountered AI agents they perceived as socially intelligent and grounded their judgments in observable behaviors, more than beliefs about AI agency or intent. We identified a support-adoption gap in acceptability judgments: participants supported the existence of Social-AI agents for others far more than for their own personal use. Our analysis uncovers layperson concerns about Social-AI, informing AI governance regarding appropriate deployment contexts, agent roles, and risks to end users.

cs.CY↗

arXiv2026

Mapping the Design Space of User Experience for Computer Use Agents

Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user experience (UX). We conducted a two-phase study to map the UX design space for computer use agents. In Phase 1, we reviewed existing systems to develop a taxonomy of UX considerations, then refined it through interviews with eight UX and AI practitioners. The resulting taxonomy included categories such as user prompts, explainability, user control, and users' mental models, with corresponding subcategories and example design features. In Phase 2, we ran a Wizard-of-Oz study with 20 participants, where a researcher acted as a web-based computer use agent and probed user reactions during normal, error-prone and risky execution. We used the findings to validate the taxonomy from Phase 1 and deepen our understand of the design space by identifying the connections between design areas and divergence in user needs and scenarios. Our taxonomy and empirical insights provide a map for developers to consider different aspects of user experience in computer use agent design and to situate their designs within users' diverse needs and scenarios.

cs.HC↗

arXiv2025

Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures

The rapid integration of generative AI into everyday life underscores the need to move beyond unidirectional alignment models that only adapt AI to human values. This workshop focuses on bidirectional human-AI alignment, a dynamic, reciprocal process where humans and AI co-adapt through interaction, evaluation, and value-centered design. Building on our past CHI 2025 BiAlign SIG and ICLR 2025 Workshop, this workshop will bring together interdisciplinary researchers from HCI, AI, social sciences and more domains to advance value-centered AI and reciprocal human-AI collaboration. We focus on embedding human and societal values into alignment research, emphasizing not only steering AI toward human values but also enabling humans to critically engage with and evolve alongside AI systems. Through talks, interdisciplinary discussions, and collaborative activities, participants will explore methods for interactive alignment, frameworks for societal impact evaluation, and strategies for alignment in dynamic contexts. This workshop aims to bridge the disciplines' gaps and establish a shared agenda for responsible, reciprocal human-AI futures.

cs.HC↗

arXiv2025

TableTalk: Scaffolding Spreadsheet Development with a Language Agent

Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language agents that observe, plan, and perform tasks, showing promise for spreadsheet creation. We present TableTalk, a spreadsheet programming agent embodying three design principles -- scaffolding, flexibility, and incrementality -- derived from studies with seven spreadsheet programmers and 85 Excel templates. TableTalk guides programmers through structured plans based on professional workflows, generating three potential next steps to adapt plans to programmer needs. It uses pre-defined tools to generate spreadsheet components and incrementally build spreadsheets. In a study with 20 programmers, TableTalk produced higher-quality spreadsheets 2.3 times more likely to be preferred than the baseline. It reduced cognitive load and thinking time by 12.6%. From this, we derive design guidelines for agentic spreadsheet programming tools and discuss implications on spreadsheet programming, end-user programming, AI-assisted programming, and human-agent collaboration.

cs.SE↗

arXiv2025

Understanding Prompt Programming Tasks and Questions

Prompting foundation models (FMs) like large language models (LLMs) have enabled new AI-powered software features (e.g., text summarization) that previously were only possible by fine-tuning FMs. Now, developers are embedding prompts in software, known as prompt programs. The process of prompt programming requires the developer to make many changes to their prompt. Yet, the questions developers ask to update their prompt is unknown, despite the answers to these questions affecting how developers plan their changes. With the growing number of research and commercial prompt programming tools, it is unclear whether prompt programmers' needs are being adequately addressed. We address these challenges by developing a taxonomy of 25 tasks prompt programmers do and 51 questions they ask, measuring the importance of each task and question. We interview 16 prompt programmers, observe 8 developers make prompt changes, and survey 50 developers. We then compare the taxonomy with 48 research and commercial tools. We find that prompt programming is not well-supported: all tasks are done manually, and 16 of the 51 questions -- including a majority of the most important ones -- remain unanswered. Based on this, we outline important opportunities for prompt programming tools.

cs.SE↗

arXiv2025

Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts

Generative pre-trained models power intelligent software features used by millions of users controlled by developer-written natural language prompts. Despite the impact of prompt-powered software, little is known about its development process and its relationship to programming. In this work, we argue that some prompts are programs and that the development of prompts is a distinct phenomenon in programming known as "prompt programming". We develop an understanding of prompt programming using Straussian grounded theory through interviews with 20 developers engaged in prompt development across a variety of contexts, models, domains, and prompt structures. We contribute 15 observations to form a preliminary understanding of current prompt programming practices. For example, rather than building mental models of code, prompt programmers develop mental models of the foundation model (FM)'s behavior on the prompt by interacting with the FM. While prior research shows that experts have well-formed mental models, we find that prompt programmers who have developed dozens of prompts still struggle to develop reliable mental models. Our observations show that prompt programming differs from traditional software development, motivating the creation of prompt programming tools and providing implications for software engineering stakeholders.

cs.SE↗

arXiv2025

How Developers Choose Debugging Strategies for Challenging Web Application Defects

Effective debugging is a crucial aspect of software development, demanding problem-solving skills, expertise, and appropriate tools. Although previous research has studied expert developers' debugging strategies, the specific factors influencing strategy choice in complex scenarios remain underexplored. To investigate these contextual factors, we conducted two studies. First, we surveyed 35 developers to identify experiences with challenging debugging problems and contextual complexities. Second, we held semi-structured interviews with 16 experienced developers to gain deeper insight into strategic reasoning for complex debugging tasks. Insights from both groups enriched our understanding of debugging strategies at different expertise levels. We found that contextual factors interact in complex ways, and combinations of factors influence strategy choice, evolving throughout the debugging process. Hypothesis making is the baseline for debugging, with experience and code familiarity crucial for strategy selection. Our results show a gap between learning and effectively practicing strategies in challenging contexts, highlighting the need for carefully designed debugging tools and educational frameworks that align with problem contexts.

cs.HC↗

arXiv2025

LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs

LLMs have shown promise in replicating human-like behavior in crowdsourcing tasks that were previously thought to be exclusive to human abilities. However, current efforts focus mainly on simple atomic tasks. We explore whether LLMs can replicate more complex crowdsourcing pipelines. We find that modern LLMs can simulate some of crowdworkers' abilities in these ``human computation algorithms,'' but the level of success is variable and influenced by requesters' understanding of LLM capabilities, the specific skills required for sub-tasks, and the optimal interaction modality for performing these sub-tasks. We reflect on human and LLMs' different sensitivities to instructions, stress the importance of enabling human-facing safeguards for LLMs, and discuss the potential of training humans and LLMs with complementary skill sets. Crucially, we show that replicating crowdsourcing pipelines offers a valuable platform to investigate 1) the relative LLM strengths on different tasks (by cross-comparing their performances on sub-tasks) and 2) LLMs' potential in complex tasks, where they can complete part of the tasks while leaving others to humans.

cs.CL↗

arXiv2024

Can GPT-4 Replicate Empirical Software Engineering Research?

Empirical software engineering research on production systems has brought forth a better understanding of the software engineering process for practitioners and researchers alike. However, only a small subset of production systems is studied, limiting the impact of this research. While software engineering practitioners could benefit from replicating research on their own data, this poses its own set of challenges, since performing replications requires a deep understanding of research methodologies and subtle nuances in software engineering data. Given that large language models (LLMs), such as GPT-4, show promise in tackling both software engineering- and science-related tasks, these models could help replicate and thus democratize empirical software engineering research. In this paper, we examine GPT-4's abilities to perform replications of empirical software engineering research on new data. We study their ability to surface assumptions made in empirical software engineering research methodologies, as well as their ability to plan and generate code for analysis pipelines on seven empirical software engineering papers. We perform a user study with 14 participants with software engineering research expertise, who evaluate GPT-4-generated assumptions and analysis plans (i.e., a list of module specifications) from the papers. We find that GPT-4 is able to surface correct assumptions, but struggles to generate ones that apply common knowledge about software engineering data. In a manual analysis of the generated code, we find that the GPT-4-generated code contains correct high-level logic, given a subset of the methodology. However, the code contains many small implementation-level errors, reflecting a lack of software engineering knowledge. Our findings have implications for leveraging LLMs for software engineering research as well as practitioner data scientists in software teams.

cs.SE↗

arXiv2024

Counterspeakers' Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate

Counterspeech, i.e., direct responses against hate speech, has become an important tool to address the increasing amount of hate online while avoiding censorship. Although AI has been proposed to help scale up counterspeech efforts, this raises questions of how exactly AI could assist in this process, since counterspeech is a deeply empathetic and agentic process for those involved. In this work, we aim to answer this question, by conducting in-depth interviews with 10 extensively experienced counterspeakers and a large scale public survey with 342 everyday social media users. In participant responses, we identified four main types of barriers and AI needs related to resources, training, impact, and personal harms. However, our results also revealed overarching concerns of authenticity, agency, and functionality in using AI tools for counterspeech. To conclude, we discuss considerations for designing AI assistants that lower counterspeaking barriers without jeopardizing its meaning and purpose.

cs.HC↗

arXiv2023

A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges

The software engineering community recently has witnessed widespread deployment of AI programming assistants, such as GitHub Copilot. However, in practice, developers do not accept AI programming assistants' initial suggestions at a high frequency. This leaves a number of open questions related to the usability of these tools. To understand developers' practices while using these tools and the important usability challenges they face, we administered a survey to a large population of developers and received responses from a diverse set of 410 developers. Through a mix of qualitative and quantitative analyses, we found that developers are most motivated to use AI programming assistants because they help developers reduce key-strokes, finish programming tasks quickly, and recall syntax, but resonate less with using them to help brainstorm potential solutions. We also found the most important reasons why developers do not use these tools are because these tools do not output code that addresses certain functional or non-functional requirements and because developers have trouble controlling the tool to generate the desired output. Our findings have implications for both creators and users of AI programming assistants, such as designing minimal cognitive effort interactions with these tools to reduce distractions for users while they are programming.

cs.SE↗

arXiv2023

NLPositionality: Characterizing Design Biases of Datasets and Models

Design biases in NLP systems, such as performance differences for different populations, often stem from their creator's positionality, i.e., views and lived experiences shaped by identity and background. Despite the prevalence and risks of design biases, they are hard to quantify because researcher, system, and dataset positionality is often unobserved. We introduce NLPositionality, a framework for characterizing design biases and quantifying the positionality of NLP datasets and models. Our framework continuously collects annotations from a diverse pool of volunteer participants on LabintheWild, and statistically quantifies alignment with dataset labels and model predictions. We apply NLPositionality to existing datasets and models for two tasks -- social acceptability and hate speech detection. To date, we have collected 16,299 annotations in over a year for 600 instances from 1,096 annotators across 87 countries. We find that datasets and models align predominantly with Western, White, college-educated, and younger populations. Additionally, certain groups, such as non-binary people and non-native English speakers, are further marginalized by datasets and models as they rank least in alignment across all tasks. Finally, we draw from prior literature to discuss how researchers can examine their own positionality and that of their datasets and models, opening the door for more inclusive NLP systems.

cs.CL↗

arXiv2023

A Qualitative Study on the Implementation Design Decisions of Developers

Decision-making is a key software engineering skill. Developers constantly make choices throughout the software development process, from requirements to implementation. While prior work has studied developer decision-making, the choices made while choosing what solution to write in code remain understudied. In this mixed-methods study, we examine the phenomenon where developers select one specific way to implement a behavior in code, given many potential alternatives. We call these decisions implementation design decisions. Our mixed-methods study includes 46 survey responses and 14 semi-structured interviews with professional developers about their decision types, considerations, processes, and expertise for implementation design decisions. We find that implementation design decisions, rather than being a natural outcome from higher levels of design, require constant monitoring of higher level design choices, such as requirements and architecture. We also show that developers have a consistent general structure to their implementation decision-making process, but no single process is exactly the same. We discuss the implications of our findings on research, education, and practice, including insights on teaching developers how to make implementation design decisions.

cs.SE↗

arXiv2022

Understanding Skills for OSS Communities on GitHub

The development of open source software (OSS) is a broad field which requires diverse skill sets. For example, maintainers help lead the project and promote its longevity, technical writers assist with documentation, bug reporters identify defects in software, and developers program the software. However, it is unknown which skills are used in OSS development as well as OSS contributors' general attitudes towards skills in OSS. In this paper, we address this gap by administering a survey to a diverse set of 455 OSS contributors. Guided by these responses as well as prior literature on software development expertise and social factors of OSS, we develop a model of skills in OSS that considers the many contexts OSS contributors work in. This model has 45 skills in the following 9 categories: technical skills, working styles, problem solving, contribution types, project-specific skills, interpersonal skills, external relations, management, and characteristics. Through a mix of qualitative and quantitative analyses, we find that OSS contributors are actively motivated to improve skills and perceive many benefits in sharing their skills with others. We then use this analysis to derive a set of design implications and best practices for those who incorporate skills into OSS tools and platforms, such as GitHub.

cs.SE↗

arXiv2022

Towards Mining OSS Skills from GitHub Activity

Open source software (OSS) development relies on diverse skill sets. However, to our knowledge, there are no tools which detect OSS-related skills. In this paper, we present a novel method to detect OSS skills and prototype it in a tool called Disko. Our approach relies on identifying relevant signals, which are measurable activities or cues associated with a skill. Our tool detects how contributors 1) teach others to be involved in OSS projects, 2) show commitment towards an OSS project, 3) have knowledge in specific programming languages, and 4) are familiar with OSS practices. We then evaluate the tool by administering a survey to 455 OSS contributors. We demonstrate that Disko yields promising results: it detects the presence of these skills with precision scores between 77% to 97%. We also find that over 54% of participants would display their high-proficiency skills. Our approach can be used to transform existing OSS experiences, such as identifying collaborators, matching mentors to mentees, and assigning project roles. Given the positive results and potential impact of our approach, we outline future research opportunities in interpreting and sharing OSS skills.

cs.SE↗