LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Documenti analoghi

• Agent-SafetyBench: Evaluating the Safety of LLM Agents
  di: Zhang, Zhexin, et al.
  Pubblicazione: (2024)
• Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
  di: Yang, Junxiao, et al.
  Pubblicazione: (2025)
• Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
  di: Zhang, Zhexin, et al.
  Pubblicazione: (2025)
• SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
  di: Tu, Jinzhe, et al.
  Pubblicazione: (2026)
• BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
  di: Yang, Junxiao, et al.
  Pubblicazione: (2025)