Ivie: Lightweight Anchored Explanations of Just-Generated Code
Litao Yan, Alyssa Hwang, Zhiyuan Wu, Andrew Head
Abstract
Programming assistants have reshaped the experience of programming into one where programmers spend less time writing and more time critically examining code. In this paper, we explore how programming assistants can be extended to accelerate the inspection of generated code. We introduce an extension to the programming assistant called Ivie, or instantly visible in-situ explanations. When using Ivie, a programmer’s generated code is instantly accompanied by explanations positioned just adjacent to the code. Our design was optimized for low-cost invocation and dismissal. Explanations are compact and informative. They describe meaningful expressions, from individual variables to entire blocks of code. We present an implementation of Ivie that forks VS Code, applying a modern LLM for timely segmentation and explanation of generated code. In a lab study, we compared Ivie to a contemporary baseline tool for code understanding. Ivie improved understanding of generated code, and was received by programmers as a highly useful, low distraction complement to the programming assistant.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers15
- Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature ReviewRock Yuren Pang, Hope Schroeder, Kynnedy Simone Smith, Solon Barocas et al.CHI 2025 · 51 citations
- How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About ItNanna Inie, Jeanette Falk, Raghavendra SelvanCHI 2025 · 33 citations
- Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming SupportKevin Pu, Daniel Lazaro, Ian Arawjo, Haijun Xia et al.CHI 2025 · 31 citations
- Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making SkillsZana Buçinca, Siddharth Swaroop, Amanda E. Paluch, Finale Doshi-Velez et al.CHI 2025 · 31 citations
- Need Help? Designing Proactive AI Assistants for ProgrammingValerie Chen, Alan Zhu, Sebastian Zhao, Hussein Mozannar et al.CHI 2025 · 23 citations
Builds on11
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 408 citations
- CodeT5+: Open Code Large Language Models for Code Understanding and GenerationYue Wang, Hung Le, Akhilesh Gotmare, Nghi D. Q. Bui et al.EMNLP 2023 · 339 citations
- Using an LLM to Help With Code UnderstandingDaye Nam, Andrew Macvean, Vincent J. Hellendoorn, Bogdan Vasilescu et al.ICSE 2024 · 264 citations
- A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and ChallengesJenny T. Liang, Chenyang Yang, Brad A. MyersICSE 2024 · 126 citations
- Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted ProgrammingHussein Mozannar, Gagan Bansal, Adam Fourney, Eric HorvitzCHI 2024 · 88 citations
Related papers
- Validating AI-Generated Code with Live ProgrammingKasra Ferdowsi, Ruanqianqian (Lisa) Huang, Michael B. James, Nadia Polikarpova et al.CHI 2024 · 27 citations
- An Exploratory Study of ML Sketches and Visual Code AssistantsLuís F. Gomes, Vincent J. Hellendoorn, Jonathan Aldrich, Rui AbreuICSE 2025 · 2 citations
- Programmers Who Use Screen Readers in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility LandscapeNan Chen, Luna K. Qiu, Arran Zeyu Wang, Zilong Wang et al.CHI 2026 · 2 citations
- CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator NeedsMajeed Kazemitabaar, Runlong Ye, Xiaoning Wang, Austin Zachary Henley et al.CHI 2024 · 246 citations
- How Do Analysts Understand and Verify AI-Assisted Data Analyses?Ken Gu, Ruoxi Shang, Tim Althoff, Chenglong Wang et al.CHI 2024 · 36 citations
