Carlos Peláez-González

According to our database, Carlos Peláez-González authored at least 4 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

A Domain-Based Taxonomy of Jailbreak Vulnerabilities in Large Language Models.

Carlos Peláez-González, Andrés Herrera-Poyatos, Cristina Zuheros, David Herrera-Poyatos, Virilo Tejedor, Francisco Herrera

CoRR, April, 2025

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability.

David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros, Andrés Herrera-Poyatos, Virilo Tejedor, Francisco Herrera, Rosana Montes

CoRR, April, 2025

The H-Elena Trojan Virus to Infect Model Weights: A Wake-Up Call on the Security Risks of Malicious Fine-Tuning.

Virilo Tejedor, Cristina Zuheros, Carlos Peláez-González, David Herrera-Poyatos, Andrés Herrera-Poyatos, Francisco Herrera

CoRR, April, 2025

2024

An In-depth Analysis of Jailbreaking Through Domain Characterization of LLM Training Sets.

Carlos Peláez-González, Andrés Herrera-Poyatos, Francisco Herrera-Triguero

Proceedings of the Hybrid Artificial Intelligent Systems - 19th International Conference, 2024