arXiv AI

On the Prospects of Dynamic LLM Conversations in Software Development

arXiv AI
Sep 10

Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks

The study investigates how users interact with ChatGPT for code generation beyond simple function-level tasks, focusing on project-level benchmarks that involve multi-class dependencies. A user study with 36 participants examined prompting patterns, screen recordings, and chat logs to identify Human‑LLM Interaction (HLI) features that influence productivity. The results highlight three consistently supportive HLI features, five guidelines to boost productivity, and a taxonomy of 29 runtime and logic errors with mitigation strategies.

By Sangwon Hyun, Hyunjun Kim, Jinhyuk Jang, Hyojin Choi, M. Ali Babar
arXiv AI
Aug 11

How to Ask the AI: A User Perspective Survey for Large Language Model Prompting

arXiv:2608. 07494v1 Announce Type: cross Abstract: AI tools like ChatGPT and DeepSeek, powered by Large Language Models (LLMs), allow users to obtain instant and effective content responses simply by typing requests, such as ``plan a three-day Vienna trip'', ``solve the attached mathematical problem'', ``draft an email to inquire review progress'', etc.

By Yiqun Zhang, Yunfan Zhang, Mingjie Zhao, Sen Feng, Yiu-ming Cheung
arXiv Machine Learning
Oct 12

Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison

The study compares human Project Manager facilitation with Llama 3.1 8B Instruct responses in scenario‑based collaborative design meetings, analyzing 199 paired contexts from the AMI Meeting Corpus. Five behavioral dimensions—contextual semantic distance, lexical elaboration, empathy‑and‑hedge lexical density, topic divergence, and phase‑vocabulary alignment—were examined. Human facilitation showed higher contextual semantic distance and empathy‑and‑hedge density, while Llama facilitation exhibited greater topic divergence, lexical elaboration, and instruction‑conditioned phase alignment.

By Mohammed Azeez Khan, Aaron Dsouza, Ashutosh Mishra, Ummul Faiz Z. Bibi, Neha K. Nair, Amar Kumar Behera
arXiv Computation and Language
Sep 22

When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation

arXiv:2609.22102v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts...

By Anubhav Gupta, Mayara Costa Figueiredo, Leticia Santos Machado, Tanner Wright, Ivan Beschastnikh, Cleidson R. B. de Souza, Gema Rodr\'iguez-P\'erez
arXiv AI
Oct 27

Developer Task Delegation to LLMs and the Trust Factor: A Mixed Methods Study

The study investigates how software developers delegate tasks to Large Language Models (LLMs), identifying four delegation modes: full, partial, self-delegation, and task avoidance. Through 22 interviews and a survey of 160 practitioners, it examines the reasons behind these choices, linking task difficulty, risk, motivation, and trust to delegation decisions. Statistical analysis shows that trust significantly influences the extent of task delegation to LLMs, offering actionable insights for human‑AI collaboration in software development.

By Samuel Ferino, Rashina Hoda, John Grundy, Christoph Treude, Hashini Gunatilake