HCI.TOPHCI, made easy

arrow_backBack to questions View categoryarrow_forward

Developer Tools and Programming Support / LLM Code Generation and Programming Assistants

Does LLM performance in software testing depend solely on model output?

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

Similar questions

helpResearch questionLLM Code Generation and Programming Assistants

How can an AI assistant supporting natural language interaction be designed to generate complex LLM workflows?

CHI '25ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines

helpResearch questionLLM Code Generation and Programming Assistants

What key role does a multi-agent architecture play in collecting requirements and generating LLM workflows?

CHI '25ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines

helpResearch questionLLM Code Generation and Programming Assistants

What advantages does ChainBuddy offer over existing tools in reducing LLM workflow design difficulty and improving satisfaction?

CHI '25ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines

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?

CHI '25How Humans Communicate Programming Tasks in Natural Language and Implications For End-User Programming with LLMs

helpResearch questionLLM Code Generation and Programming Assistants

What are the effects of programming experience, example use, and interactivity on task description and understanding?

CHI '25How Humans Communicate Programming Tasks in Natural Language and Implications For End-User Programming with LLMs

helpResearch questionLLM Code Generation and Programming Assistants

How do LLMs such as GPT-4 differ in performance when directly answering questions versus generating code?

CHI '25How Humans Communicate Programming Tasks in Natural Language and Implications For End-User Programming with LLMs

Related papers

ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines

Jingyue Zhang, Ian Arawjo

How Humans Communicate Programming Tasks in Natural Language and Implications For End-User Programming with LLMs

Madison Pickering, Helena Williams, Alison Gan

How Scientists Use Large Language Models to Program

Gabrielle O'Brien

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

How Beginning Programmers and Code LLMs (Mis)read Each Other

Sydney Nguyen, Hannah McLean Babe, Yangtian Zi

"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

Exploring the Learnability of Program Synthesizers by Novice Programmers

Dhanya Jayagopal, Justin Lubin, Sarah E. Chasins