4 papers
Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework
David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros +3
Large Language Models (LLMs) are increasingly being deployed in high-risk domains where opacity, bias, and instability undermine trust and accountability. Traditional explainabilit…
A Domain-Based Taxonomy of Jailbreak Vulnerabilities in Large Language Models
Carlos Peláez-González, Andrés Herrera-Poyatos, Cristina Zuheros +3
The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also fac…
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 +4
Large Language Models (LLMs) have significantly advanced sentiment analysis, yet their inherent uncertainty and variability pose critical challenges to achieving reliable and consi…
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 +3
Large Language Models (LLMs) offer powerful capabilities in text generation and are increasingly adopted across a wide range of domains. However, their open accessibility and fine-…