How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Corbo, Simone, Bancale, Luca, De Gennaro, Valeria, Lestingi, Livia, Scotti, Vincenzo, Camilli, Matteo
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots
di: Dettori, Francesco, et al.
Pubblicazione: (2026)

Automated Detection and Mitigation of Dependability Failures in Healthcare Scenarios through Digital Twins
di: Guindani, Bruno, et al.
Pubblicazione: (2026)

Towards an Agentic LLM-based Approach to Requirement Formalization from Unstructured Specifications
di: Tagliaferro, Alberto, et al.
Pubblicazione: (2026)

Can LLMs Solve Science or Just Write Code? Evaluating Quantum Solver Generation
di: Baresi, Luciano, et al.
Pubblicazione: (2026)

The Landscape of Toxicity: An Empirical Investigation of Toxicity on GitHub
di: Sarker, Jaydeb, et al.
Pubblicazione: (2025)

Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness
di: Wang, Wenxuan
Pubblicazione: (2024)

What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation
di: Yin, Xin, et al.
Pubblicazione: (2024)

Beyond Monolithic Models: Symbolic Seams for Composable Neuro-Symbolic Architectures
di: Schuler, Nicolas, et al.
Pubblicazione: (2026)

A Roadmap for Tamed Interactions with Large Language Models
di: Scotti, Vincenzo, et al.
Pubblicazione: (2025)

Understanding and Predicting Derailment in Toxic Conversations on GitHub
di: Imran, Mia Mohammad, et al.
Pubblicazione: (2025)

A Large-Scale Study of Call Graph-based Impact Prediction using Mutation Testing
di: Musco, Vincenzo, et al.
Pubblicazione: (2018)

Efficient Detection of Toxic Prompts in Large Language Models
di: Liu, Yi, et al.
Pubblicazione: (2024)

Real-Time Toxicity Filtering for Open-Source Code Reviews
di: Anindya, Md Awsaf Alam, et al.
Pubblicazione: (2026)

"Silent Is Not Actually Silent": An Investigation of Toxicity on Bug Report Discussion
di: Imran, Mia Mohammad, et al.
Pubblicazione: (2025)

How Low Can You Go? The Data-Light SE Challenge
di: Ganguly, Kishan Kumar, et al.
Pubblicazione: (2025)

Can Large Language Models Write Good Property-Based Tests?
di: Vikram, Vasudev, et al.
Pubblicazione: (2023)

Improving the Readability of Automatically Generated Tests using Large Language Models
di: Biagiola, Matteo, et al.
Pubblicazione: (2024)

What You Need is What You Get: Theory of Mind for an LLM-Based Code Understanding Assistant
di: Richards, Jonan, et al.
Pubblicazione: (2024)

Assessing the Influence of Toxic and Gender Discriminatory Communication on Perceptible Diversity in OSS Projects
di: Sultana, Sayma, et al.
Pubblicazione: (2024)

Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering
di: Zhuo, Hao, et al.
Pubblicazione: (2025)

STELLAR: A Search-Based Testing Framework for Large Language Model Applications
di: Sorokin, Lev, et al.
Pubblicazione: (2026)

What You Use is What You Get: Unforced Errors in Studying Cultural Aspects in Agile Software Development
di: Neumann, Michael, et al.
Pubblicazione: (2024)

Can AI Agents Generate Microservices? How Far are We?
di: Adnan, Bassam, et al.
Pubblicazione: (2026)

ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering
di: Anindya, MD Awsaf Alam, et al.
Pubblicazione: (2026)

Analyzing Toxicity in Open Source Software Communications Using Psycholinguistics and Moral Foundations Theory
di: Ehsani, Ramtin, et al.
Pubblicazione: (2024)

Towards Automated Page Object Generation for Web Testing using Large Language Models
di: Karagöz, Betül, et al.
Pubblicazione: (2026)

Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search
di: Zhang, Jiayi, et al.
Pubblicazione: (2025)

SafeTune: Search-based Harmfulness Minimisation for Large Language Models
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2026)

You Can REST Now: Automated REST API Documentation and Testing via LLM-Assisted Request Mutations
di: Decrop, Alix, et al.
Pubblicazione: (2024)

I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution
di: Choi, Soohyeon, et al.
Pubblicazione: (2025)

Search-based Testing of Simulink Models with Requirements Tables
di: Formica, Federico, et al.
Pubblicazione: (2025)

LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
di: Huang, Linghan, et al.
Pubblicazione: (2025)

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

You Augment Me: Exploring ChatGPT-based Data Augmentation for Semantic Code Search
di: Wang, Yanlin, et al.
Pubblicazione: (2024)

Search-based DNN Testing and Retraining with GAN-enhanced Simulations
di: Attaoui, Mohammed Oualid, et al.
Pubblicazione: (2024)

Search-based Hyperparameter Tuning for Python Unit Test Generation
di: Lukasczyk, Stephan, et al.
Pubblicazione: (2025)

Toward Systematic Counterfactual Fairness Evaluation of Large Language Models: The CAFFE Framework
di: Parziale, Alessandra, et al.
Pubblicazione: (2025)

XMutant: XAI-based Fuzzing for Deep Learning Systems
di: Chen, Xingcheng, et al.
Pubblicazione: (2025)

Can Large Language Models Model Programs Formally?
di: Chen, Zhiyong, et al.
Pubblicazione: (2026)

Can Large Language Models Generate Geospatial Code?
di: Hou, Shuyang, et al.
Pubblicazione: (2024)