SafeTune: Search-based Harmfulness Minimisation for Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	d'Aloisio, Giordano, Williams, David, Annunziata, Giusy, Fei, Zhiwei, Di Marco, Antinisca, Sarro, Federica
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2024)

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias
di: Fadahunsi, Tosin, et al.
Pubblicazione: (2025)

Investigating the Role of LLMs Hyperparameter Tuning and Prompt Engineering to Support Domain Modeling
di: Bulhakov, Vladyslav, et al.
Pubblicazione: (2025)

MANILA: A Low-Code Application to Benchmark Machine Learning Models and Fairness-Enhancing Methods
di: d'Aloisio, Giordano
Pubblicazione: (2025)

How fair are we? From conceptualization to automated assessment of fairness definitions
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2024)

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2025)

Exploring LLM-Driven Explanations for Quantum Algorithms
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2024)

FairRF: Multi-Objective Search for Single and Intersectional Software Fairness
di: d'Alosio, Giordano, et al.
Pubblicazione: (2026)

REPAIR Approach for Social-based City Reconstruction Planning in case of natural disasters
di: Mudassir, Ghulam, et al.
Pubblicazione: (2025)

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
di: Li, Xiang, et al.
Pubblicazione: (2026)

BayesInsights: Modelling Software Delivery and Developer Experience with Bayesian Networks at Bloomberg
di: Kirbas, Serkan, et al.
Pubblicazione: (2026)

A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
di: Boubekraoui, Maryam, et al.
Pubblicazione: (2026)

Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection
di: Williams, David, et al.
Pubblicazione: (2025)

Psychological Safety Framework in Pull-based Open Source Projects
di: Sesari, Emeralda, et al.
Pubblicazione: (2025)

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
di: Majgaonkar, Oorja, et al.
Pubblicazione: (2025)

Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
di: Pinna, Giovanni, et al.
Pubblicazione: (2026)

Echo: Graph-Enhanced Retrieval and Execution Feedback for Issue Reproduction Test Generation
di: Fei, Zhiwei, et al.
Pubblicazione: (2026)

VAMP: Visual Analytics for Microservices Performance
di: Traini, Luca, et al.
Pubblicazione: (2024)

How Do Communities of ML-Enabled Systems Smell? A Cross-Sectional Study on the Prevalence of Community Smells
di: Annunziata, Giusy, et al.
Pubblicazione: (2025)

Simplicity by Obfuscation: Evaluating LLM-Driven Code Transformation with Semantic Elasticity
di: De Tomasi, Lorenzo, et al.
Pubblicazione: (2025)

Understanding Fairness in Software Engineering: Insights from Stack Exchange
di: Sesari, Emeralda, et al.
Pubblicazione: (2024)

It is Giving Major Satisfaction: Why Fairness Matters for Software Practitioners
di: Sesari, Emeralda, et al.
Pubblicazione: (2024)

Unveiling Practical Shortcomings of Patch Overfitting Detection Techniques
di: Williams, David, et al.
Pubblicazione: (2026)

A Decision Tree to Shepherd Scientists through Data Retrievability
di: Bianchi, Andrea, et al.
Pubblicazione: (2023)

Hot Fixing Software: A Comprehensive Review of Terminology, Techniques, and Applications
di: Hanna, Carol, et al.
Pubblicazione: (2024)

Unveiling Overlooked Performance Variance in Serverless Computing
di: Wen, Jinfeng, et al.
Pubblicazione: (2023)

HotBugs.jar: A Benchmark of Hot Fixes for Time-Critical Bugs
di: Hanna, Carol, et al.
Pubblicazione: (2025)

From Research to Practice: An Interactive Rapid Review of Autonomous Driving System Testing in Industry
di: Song, Qunying, et al.
Pubblicazione: (2026)

Architectural Support for Software Performance in Continuous Software Engineering: A Systematic Mapping Study
di: Eramo, Romina, et al.
Pubblicazione: (2023)

Test-based Patch Clustering for Automatically-Generated Patches Assessment
di: Martinez, Matias, et al.
Pubblicazione: (2022)

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation
di: Jia, Haoxiang, et al.
Pubblicazione: (2025)

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
di: Li, Xiang, et al.
Pubblicazione: (2026)

Fairness Testing: A Comprehensive Survey and Analysis of Trends
di: Chen, Zhenpeng, et al.
Pubblicazione: (2022)

Automated Harmfulness Testing for Code Large Language Models
di: Tan, Honghao, et al.
Pubblicazione: (2025)

Generative AI for Testing of Autonomous Driving Systems: A Survey
di: Song, Qunying, et al.
Pubblicazione: (2025)

On The Effectiveness of One-Class Support Vector Machine in Different Defect Prediction Scenarios
di: Moussa, Rebecca, et al.
Pubblicazione: (2022)

Charting The Evolution of Solidity Error Handling
di: Mitropoulos, Charalambos, et al.
Pubblicazione: (2024)

A Comprehensive Study of Bugs in Modern Distributed Deep Learning Systems
di: Ma, Xiaoxue, et al.
Pubblicazione: (2025)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
di: Gong, Jingzhi, et al.
Pubblicazione: (2026)

LLM-Based Misconfiguration Detection for AWS Serverless Computing
di: Wen, Jinfeng, et al.
Pubblicazione: (2024)