Cover Image

Studying How Configurations Impact Code Generation in LLMs: the Case of ChatGPT

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Donato, Benedetta, Mariani, Leonardo, Micucci, Daniela, Riganelli, Oliviero
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Possibility of Breaking Copyleft Licenses When Reusing Code Generated by ChatGPT
by: Colombo, Gaia, et al.
Published: (2025)

MultiMind: A Plug-in for the Implementation of Development Tasks Aided by AI Assistants
by: Donato, Benedetta, et al.
Published: (2025)

Assessing AI-Based Code Assistants in Method Generation Tasks
by: Corso, Vincenzo, et al.
Published: (2024)

Generating Java Methods: An Empirical Assessment of Four AI-Based Code Assistants
by: Corso, Vincenzo, et al.
Published: (2024)

Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot
by: Fagadau, Ionut Daniel, et al.
Published: (2024)

Testing in the Evolving World of DL Systems:Insights from Python GitHub Projects
by: Ali, Qurban, et al.
Published: (2024)

From PREVENTion to REACTion: Enhancing Failure Resolution in Naval Systems
by: Rossi, Maria Teresa, et al.
Published: (2025)

OpenCat: Improving Interoperability of ADS Testing
by: Ali, Qurban, et al.
Published: (2025)

Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems
by: Ali, Qurban, et al.
Published: (2026)

ReProbe: An Architecture for Reconfigurable and Adaptive Probes
by: Alessi, Federico, et al.
Published: (2024)

Automated Testing of Task-based Chatbots: How Far Are We?
by: Clerissi, Diego, et al.
Published: (2026)

Bug Whispering: Towards Audio Bug Reporting
by: Masserini, Elena, et al.
Published: (2025)

"Where is My Troubleshooting Procedure?": Studying the Potential of RAG in Assisting Failure Resolution of Large Cyber-Physical System
by: Rossi, Maria Teresa, et al.
Published: (2026)

An Empirical Study of the Non-determinism of ChatGPT in Code Generation
by: Ouyang, Shuyin, et al.
Published: (2023)

How to Refactor this Code? An Exploratory Study on Developer-ChatGPT Refactoring Conversations
by: AlOmar, Eman Abdullah, et al.
Published: (2024)

Self-collaboration Code Generation via ChatGPT
by: Dong, Yihong, et al.
Published: (2023)

Why Do Developers Engage with ChatGPT in Issue-Tracker? Investigating Usage and Reliance on ChatGPT-Generated Code
by: Das, Joy Krishan, et al.
Published: (2024)

Towards Multi-Platform Mutation Testing of Task-based Chatbots
by: Clerissi, Diego, et al.
Published: (2025)

Assessing Task-based Chatbots: Snapshot and Curated Datasets for Dialogflow
by: Masserini, Elena, et al.
Published: (2026)

Anonymizing Test Data in Android: Does It Hurt?
by: Masserini, Elena, et al.
Published: (2024)

WildCode: An Empirical Analysis of Code Generated by ChatGPT
by: Khanmohammadi, Kobra, et al.
Published: (2025)

DevGPT: Studying Developer-ChatGPT Conversations
by: Xiao, Tao, et al.
Published: (2023)

How I Learned to Stop Worrying and Love ChatGPT
by: Przymus, Piotr, et al.
Published: (2025)

No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT
by: Liu, Zhijie, et al.
Published: (2023)

Can ChatGPT Generate Realistic Synthetic System Requirement Specifications? Results of a Case Study
by: Mattukat, Alex R., et al.
Published: (2026)

Towards the Assessment of Task-based Chatbots: From the TOFU-R Snapshot to the BRASATO Curated Dataset
by: Masserini, Elena, et al.
Published: (2025)

ChatGPT for Code Refactoring: Analyzing Topics, Interaction, and Effective Prompts
by: AlOmar, Eman Abdullah, et al.
Published: (2025)

Is ChatGPT 3 safe for students?
by: Kotovich, Julia, et al.
Published: (2024)

Unveiling the Role of ChatGPT in Software Development: Insights from Developer-ChatGPT Interactions on GitHub
by: Li, Ruiyin, et al.
Published: (2025)

Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?
by: Yu, Xiao, et al.
Published: (2024)

ChatGPT vs. DeepSeek: A Comparative Study on AI-Based Code Generation
by: Manik, Md Motaleb Hossen
Published: (2025)

SOGPTSpotter: Detecting ChatGPT-Generated Answers on Stack Overflow
by: Ma, Suyu, et al.
Published: (2026)

An Empirical Study of ChatGPT-Related Projects and Their Issues on GitHub
by: Lin, Zheng, et al.
Published: (2024)

Investigating the Utility of ChatGPT in the Issue Tracking System: An Exploratory Study
by: Das, Joy Krishan, et al.
Published: (2024)

When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?
by: Chen, Chong, et al.
Published: (2023)

An Analysis of Automated Use Case Component Extraction from Scenarios using ChatGPT
by: KC, Pragyan, et al.
Published: (2024)

Pros and Cons! Evaluating ChatGPT on Software Vulnerability
by: Yin, Xin
Published: (2024)

The role of library versions in Developer-ChatGPT conversations
by: Raj, Rachna, et al.
Published: (2024)

Evaluating and Improving ChatGPT-Based Expansion of Abbreviations
by: Jiang, Yanjie, et al.
Published: (2024)

ChatGPT in Introductory Programming: Counterbalanced Evaluation of Code Quality, Conceptual Learning, and Student Perceptions
by: Andleeb, Shiza, et al.
Published: (2025)