RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

Documenti analoghi

• MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space
  di: Tang, Yihong, et al.
  Pubblicazione: (2024)
• Do LLMs Have the Generalization Ability in Conducting Causal Inference?
  di: Wang, Chen, et al.
  Pubblicazione: (2024)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection
  di: Zhao, Yachao, et al.
  Pubblicazione: (2025)
• Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
  di: Tang, Yihong, et al.
  Pubblicazione: (2025)
• Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
  di: Tang, Yihong, et al.
  Pubblicazione: (2026)