Copertina

How the Training Procedure Impacts the Performance of Deep Learning-based Vulnerability Patching

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mastropaolo, Antonio, Nardone, Vittoria, Bavota, Gabriele, Di Penta, Massimiliano
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study
di: Tufano, Rosalia, et al.
Pubblicazione: (2024)

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

Deep Learning-based Code Completion: On the Impact on Performance of Contextual Information
di: Ciniselli, Matteo, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions
di: Ciniselli, Matteo, et al.
Pubblicazione: (2024)

Augmenting Software Bills of Materials with Software Vulnerability Description: A Preliminary Study on GitHub
di: Fucci, Davide, et al.
Pubblicazione: (2025)

From Human to Machine Refactoring: Assessing GPT-4's Impact on Python Class Quality and Readability
di: Midolo, Alessandro, et al.
Pubblicazione: (2026)

Automated Refactoring of Non-Idiomatic Python Code: A Differentiated Replication with LLMs
di: Midolo, Alessandro, et al.
Pubblicazione: (2025)

Why Personalizing Deep Learning-Based Code Completion Tools Matters
di: Giagnorio, Alessandro, et al.
Pubblicazione: (2025)

How do Copilot Suggestions Impact Developers' Frustration and Productivity?
di: Guglielmi, Emanuela, et al.
Pubblicazione: (2025)

Automating Code Review: A Systematic Literature Review
di: Tufano, Rosalia, et al.
Pubblicazione: (2025)

Machine Learning in the Wild: Early Evidence of Non-Compliant ML-Automation in Open-Source Software
di: Arshid, Zohaib, et al.
Pubblicazione: (2026)

How are MLOps Frameworks Used in Open Source Projects? An Empirical Characterization
di: Zampetti, Fiorella, et al.
Pubblicazione: (2026)

Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?
di: Tufano, Rosalia, et al.
Pubblicazione: (2024)

SEART Data Hub: Streamlining Large-Scale Source Code Mining and Pre-Processing
di: Dabić, Ozren, et al.
Pubblicazione: (2024)

Studying Quality Improvements Recommended via Manual and Automated Code Review
di: Crupi, Giuseppe, et al.
Pubblicazione: (2026)

Improving Code Generation via Small Language Model-as-a-judge
di: Crupi, Giuseppe, et al.
Pubblicazione: (2026)

Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation
di: Improta, Cristina, et al.
Pubblicazione: (2025)

"Let it be Chaos in the Plumbing!" Usage and Efficacy of Chaos Engineering in DevOps Pipelines
di: Fossati, Stefano, et al.
Pubblicazione: (2025)

Automatic Categorization of GitHub Actions with Transformers and Few-shot Learning
di: Nguyen, Phuong T., et al.
Pubblicazione: (2024)

An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation
di: Cheng, Zaiyu, et al.
Pubblicazione: (2026)

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

Enhancing Code Generation for Low-Resource Languages: No Silver Bullet
di: Giagnorio, Alessandro, et al.
Pubblicazione: (2025)

Do LLMs Provide Links to Code Similar to what they Generate? A Study with Gemini and Bing CoPilot
di: Bifolco, Daniele, et al.
Pubblicazione: (2025)

On the Generalizability of Transformer Models to Code Completions of Different Lengths
di: Cooper, Nathan, et al.
Pubblicazione: (2025)

Evaluating Pre-Trained Models for Multi-Language Vulnerability Patching
di: Khan, Zanis Ali, et al.
Pubblicazione: (2025)

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

Learning Graph-based Patch Representations for Identifying and Assessing Silent Vulnerability Fixes
di: Han, Mei, et al.
Pubblicazione: (2024)

BOMs Away! Inside the Minds of Stakeholders: A Comprehensive Study of Bills of Materials for Software Systems
di: Stalnaker, Trevor, et al.
Pubblicazione: (2023)

CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
di: Bifolco, Daniele, et al.
Pubblicazione: (2025)

Similar but Patched Code Considered Harmful -- The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove Them
di: Tan, Zixuan, et al.
Pubblicazione: (2024)

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

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