Universal and Context-Independent Triggers for Precise Control of LLM Outputs

Documenti analoghi

• Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
  di: Wang, Yanbo, et al.
  Pubblicazione: (2026)
• Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
  di: Xing, Wenpeng, et al.
  Pubblicazione: (2025)
• Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
  di: Yu, Yongcan, et al.
  Pubblicazione: (2025)
• Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts
  di: Uenal, Fatih
  Pubblicazione: (2026)
• CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
  di: Zhang, Yu, et al.
  Pubblicazione: (2025)