Cover Image

An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Zaiyu, Mastropaolo, Antonio
Format:	Preprint
Published:	2026
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prompt-Driven Code Summarization: A Systematic Literature Review
by: Farjana, Afia, et al.
Published: (2026)

Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization
by: Afrin, Saima, et al.
Published: (2026)

Is Quantization a Deal-breaker? Empirical Insights from Large Code Models
by: Afrin, Saima, et al.
Published: (2025)

A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models
by: Afrin, Saima, et al.
Published: (2025)

Parameter-Efficient Multi-Task Fine-Tuning in Code-Related Tasks
by: Haque, Md Zahidul, et al.
Published: (2026)

Evaluating the Impact of Post-Training Quantization on Large Language Models for Code Generation
by: Giagnorio, Alessandro, et al.
Published: (2025)

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
by: Shin, Jiho, et al.
Published: (2023)

Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?
by: Vitale, Antonio, et al.
Published: (2025)

Fine-grained Multi-Document Extraction and Generation of Code Change Rationale
by: Sun, Mehedi, et al.
Published: (2026)

On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization
by: Crupi, Giuseppe, et al.
Published: (2025)

A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm
by: Mastropaolo, Antonio, et al.
Published: (2025)

Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
by: Midolo, Alessandro, et al.
Published: (2026)

Code Review Automation: Strengths and Weaknesses of the State of the Art
by: Tufano, Rosalia, et al.
Published: (2024)

Resource-Efficient & Effective Code Summarization
by: Afrin, Saima, et al.
Published: (2025)

Rethinking Software Empirical Studies with Structural Causal Models
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2026)

Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation
by: Fang, Sen, et al.
Published: (2025)

Detect Repair Verify for Securing LLM Generated Code: A Multi-Language Empirical Study
by: Cheng, Cheng
Published: (2026)

Towards Summarizing Code Snippets Using Pre-Trained Transformers
by: Mastropaolo, Antonio, et al.
Published: (2024)

Detect--Repair--Verify for LLM-Generated Code: A Multi-Language, Multi-Granularity Empirical Study
by: Cheng, Cheng
Published: (2026)

On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies
by: Jahromi, Ali Soltanian Fard, et al.
Published: (2026)

Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study
by: Liu, Shuo, et al.
Published: (2024)

Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
by: Ji, Kexing, et al.
Published: (2025)

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning
by: Le, Huy, et al.
Published: (2025)

Assessing Small Language Models for Code Generation: An Empirical Study with Benchmarks
by: Hasan, Md Mahade, et al.
Published: (2025)

When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
by: AKLI, Amal, et al.
Published: (2026)

A Taxonomy of Self-Admitted Technical Debt in Deep Learning Systems
by: Pepe, Federica, et al.
Published: (2024)

Developers and Generative AI: A Study of Self-Admitted Usage in Open Source Projects
by: Tufano, Rosalia, et al.
Published: (2026)

Do Prompt Patterns Affect Code Quality? A First Empirical Assessment of ChatGPT-Generated Code
by: Della Porta, Antonio, et al.
Published: (2025)

Smart but Costly? Benchmarking LLMs on Functional Accuracy and Energy Efficiency
by: Mehditabar, Mohammadjavad, et al.
Published: (2025)

An Empirical Study of Sustainability in Prompt-driven Test Script Generation Using Small Language Models
by: Kumari, Pragati, et al.
Published: (2026)

Are Coding Agents Generating Over-Mocked Tests? An Empirical Study
by: Hora, Andre, et al.
Published: (2026)

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

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
by: Yang, Zezhou, et al.
Published: (2025)

Prompting in the Wild: An Empirical Study of Prompt Evolution in Software Repositories
by: Tafreshipour, Mahan, et al.
Published: (2024)

Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study
by: Vukovic, Maja, et al.
Published: (2026)

An Empirical Study on the Impact of Gender Diversity on Code Quality in AI Systems
by: Cynthia, Shamse Tasnim, et al.
Published: (2025)

How the Training Procedure Impacts the Performance of Deep Learning-based Vulnerability Patching
by: Mastropaolo, Antonio, et al.
Published: (2024)

Rethinking Code Review Workflows with LLM Assistance: An Empirical Study
by: Aðalsteinsson, Fannar Steinn, et al.
Published: (2025)

Zero-Shot Code Representation Learning via Prompt Tuning
by: Cui, Nan, et al.
Published: (2024)

Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automation
by: Pornprasit, Chanathip, et al.
Published: (2024)