You Know What I'm Saying: Jailbreak Attack via Implicit Reference

Documenti analoghi

• Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
  di: Luo, Wen, et al.
  Pubblicazione: (2026)
• You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
  di: Gaznepoglu, Ünal Ege, et al.
  Pubblicazione: (2025)
• Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles
  di: Wang, Kuang, et al.
  Pubblicazione: (2025)
• Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
  di: Tan, Chenchen, et al.
  Pubblicazione: (2025)
• What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
  di: Lee, Joosung, et al.
  Pubblicazione: (2026)