helpResearch questionLLM Code Generation and Programming Assistants
How can an AI assistant supporting natural language interaction be designed to generate complex LLM workflows?Direction: Developer Tools and Programming Support
LLM Code Generation and Programming Assistants
Stats are based on currently indexed question data; missing sources remain visible.
44
items
11
sources
2025
latest
All questions
44 items
helpResearch questionLLM Code Generation and Programming Assistants
What key role does a multi-agent architecture play in collecting requirements and generating LLM workflows?helpResearch questionLLM Code Generation and Programming Assistants
What advantages does ChainBuddy offer over existing tools in reducing LLM workflow design difficulty and improving satisfaction?lightbulbPractical problemLLM Code Generation and Programming Assistants
Users often feel lost when setting up LLM workflows and evaluation tasks.helpResearch questionLLM Code Generation and Programming Assistants
How can information processing tasks (IPTs) be described in natural language to optimize communication between humans and LLMs?helpResearch questionLLM Code Generation and Programming Assistants
What are the effects of programming experience, example use, and interactivity on task description and understanding?helpResearch questionLLM Code Generation and Programming Assistants
How do LLMs such as GPT-4 differ in performance when directly answering questions versus generating code?lightbulbPractical problemLLM Code Generation and Programming Assistants
Non-technical users struggle to efficiently describe programming tasks in natural language to interact with AI.helpResearch questionLLM Code Generation and Programming Assistants
How do scientists use Code LLMs (code generation tools based on large language models)?helpResearch questionLLM Code Generation and Programming Assistants
What strategies do scientists use to verify Code LLM-generated code, and are they effective?helpResearch questionLLM Code Generation and Programming Assistants
How do scientific programmers' behaviors and goals differ significantly from traditional programmers?lightbulbPractical problemLLM Code Generation and Programming Assistants
Scientists may produce experimental analysis errors due to programming mistakes, undermining credibility of research conclusions.helpResearch questionLLM Code Generation and Programming Assistants
How can LLM-driven assistants (e.g., Copilot) help users learn software features while automating task completion?helpResearch questionLLM Code Generation and Programming Assistants
What behaviors and preferences do users exhibit when using fully automated versus semi-automated assistants?helpResearch questionLLM Code Generation and Programming Assistants
How can semi-automated assistants improve user experience through dynamic visual guidance and adaptive design?lightbulbPractical problemLLM Code Generation and Programming Assistants
Users struggle to learn software features while using AI assistants to complete tasks and lack a sense of control.helpResearch questionLLM Code Generation and Programming Assistants
How can freehand annotations dynamically edit code structure, flow, and syntax?UIST '24Code Shaping: Iterative Code Editing with Free-form Sketching
helpResearch questionLLM Code Generation and Programming Assistants
How can the ambiguity of handwritten annotations be resolved to improve AI understanding of code editing intent?UIST '24Code Shaping: Iterative Code Editing with Free-form Sketching
helpResearch questionLLM Code Generation and Programming Assistants
How do handwritten annotations affect coding efficiency and interactive code generation processes?UIST '24Code Shaping: Iterative Code Editing with Free-form Sketching
lightbulbPractical problemLLM Code Generation and Programming Assistants
When programmers modify code with handwritten annotations, tools cannot automatically understand and transform their intent.UIST '24Code Shaping: Iterative Code Editing with Free-form Sketching
helpResearch questionLLM Code Generation and Programming Assistants
Does LLM performance in software testing depend solely on model output?UIST '24Pay Attention! Human-Centric Improvements of LLM-based Interfaces for Assisting Software Test Case Development
helpResearch questionLLM Code Generation and Programming Assistants
How does HCI interface design affect user creativity and interaction efficiency?UIST '24Pay Attention! Human-Centric Improvements of LLM-based Interfaces for Assisting Software Test Case Development
helpResearch questionLLM Code Generation and Programming Assistants
How do different interaction design strategies affect user productivity, creativity, and attention allocation?UIST '24Pay Attention! Human-Centric Improvements of LLM-based Interfaces for Assisting Software Test Case Development
lightbulbPractical problemLLM Code Generation and Programming Assistants
Traditional LLM interfaces may reduce user creativity and efficiency, affecting testing outcomes.UIST '24Pay Attention! Human-Centric Improvements of LLM-based Interfaces for Assisting Software Test Case Development
helpResearch questionLLM Code Generation and Programming Assistants
How do novice programmers interact with code generation models (Code LLMs), and what major difficulties do they face?helpResearch questionLLM Code Generation and Programming Assistants
What specific problems exist in novices' natural language descriptions for code generation?helpResearch questionLLM Code Generation and Programming Assistants
How can experimental design systematically reveal cognitive challenges that affect code generation outcomes?lightbulbPractical problemLLM Code Generation and Programming Assistants
Novice programmers struggle to efficiently generate correct code with existing code generation tools.helpResearch questionLLM Code Generation and Programming Assistants
How can multi-turn dialogue improve programming assistants' contextual understanding (e.g., code generation)?IUI '23The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development
helpResearch questionLLM Code Generation and Programming Assistants
Can programming assistants with conversational capabilities more effectively solve progressively complex programming tasks?IUI '23The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development
helpResearch questionLLM Code Generation and Programming Assistants
How does LLM-based programming assistant performance in user code generation compare with traditional tools?IUI '23The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development
lightbulbPractical problemLLM Code Generation and Programming Assistants
Programmers often face programming tasks, but existing tools struggle to provide context-aware multi-turn support.IUI '23The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development
helpResearch questionLLM Code Generation and Programming Assistants
How do users effectively communicate with code-generating LLMs, especially when choosing appropriate abstraction levels?helpResearch questionLLM Code Generation and Programming Assistants
Can introducing embodied abstraction matching help users better understand code generation and improve error recovery?helpResearch questionLLM Code Generation and Programming Assistants
In natural language programming for tabular data analysis, how can systems be designed to support users' intent expression?lightbulbPractical problemLLM Code Generation and Programming Assistants
Non-professional programming users struggle to generate accurate code through natural language.helpResearch questionLLM Code Generation and Programming Assistants
Which design factors most affect learnability when novice programmers use program synthesis tools?helpResearch questionLLM Code Generation and Programming Assistants
How do different triggering mechanisms (automatic or manual) affect novices' learning experience?helpResearch questionLLM Code Generation and Programming Assistants
How much do complex or large specifications in program synthesis tools affect the learning process?lightbulbPractical problemLLM Code Generation and Programming Assistants
Novice programmers often feel confused and find code generation tools difficult to use.helpResearch questionLLM Code Generation and Programming Assistants
How can developers use annotation approaches to simplify the design and implementation of mobile app privacy notices?UbiComp '21Honeysuckle: Annotation-Guided Code Generation of In-App Privacy Notices
helpResearch questionLLM Code Generation and Programming Assistants
Can annotation-driven privacy notice code generation improve development efficiency and reduce cognitive load?UbiComp '21Honeysuckle: Annotation-Guided Code Generation of In-App Privacy Notices
helpResearch questionLLM Code Generation and Programming Assistants
Can the Honeysuckle tool significantly improve the consistency and flexibility of privacy notices?UbiComp '21Honeysuckle: Annotation-Guided Code Generation of In-App Privacy Notices
lightbulbPractical problemLLM Code Generation and Programming Assistants
Users struggle to obtain clear information about privacy practices, leading to distrust of apps.UbiComp '21Honeysuckle: Annotation-Guided Code Generation of In-App Privacy Notices
Related papers
CHI 2025
ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines
Jingyue Zhang, Ian Arawjo
CHI 2025
How Humans Communicate Programming Tasks in Natural Language and Implications For End-User Programming with LLMs
Madison Pickering, Helena Williams, Alison Gan
CHI 2025
How Scientists Use Large Language Models to Program
Gabrielle O'Brien
CHI 2025
Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
Anjali Khurana, Xiaotian Su, April Yi Wang
CHI 2024
How Beginning Programmers and Code LLMs (Mis)read Each Other
Sydney Nguyen, Hannah McLean Babe, Yangtian Zi
CHI 2023
"What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
Michael Xieyang Liu, Advait Sarkar, Carina Negreanu
UIST 2022
Exploring the Learnability of Program Synthesizers by Novice Programmers
Dhanya Jayagopal, Justin Lubin, Sarah E. Chasins
Adjacent categories
Developer Tools and Programming Support
Coding Assistants and Multi-Turn Code Support
109 items
Developer Tools and Programming Support
Electronic Circuit Fabrication and Hardware Design Tools
28 items
Developer Tools and Programming Support
AI Code Translation and Error Repair Support
20 items
Developer Tools and Programming Support
Natural Language Formulas in Spreadsheets
20 items
Developer Tools and Programming Support
Analysis Workflows and Information Extraction Tools
16 items
Developer Tools and Programming Support
Debugging Support and Fault Localization
12 items
Developer Tools and Programming Support
Intermittent Computing Programming and Energy-Adaptive Tools
12 items
Developer Tools and Programming Support
Notational Programming and Code-Diagram Hybrid Input
12 items