Risk and Response in Large Language Models: Evaluating Key Threat Categories

Documenti analoghi

• The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance
  di: Salinas, Abel, et al.
  Pubblicazione: (2024)
• Knowledge Graph Analysis of Legal Understanding and Violations in LLMs
  di: Jha, Abha, et al.
  Pubblicazione: (2025)
• The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations
  di: Salinas, Abel, et al.
  Pubblicazione: (2023)
• Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
  di: Dorn, Rebecca, et al.
  Pubblicazione: (2024)
• Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?
  di: Atil, Berk, et al.
  Pubblicazione: (2025)