AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

Documenti analoghi

• Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
  di: Li, Tung-Ling, et al.
  Pubblicazione: (2025)
• Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment
  di: Rad, Melissa Kazemi, et al.
  Pubblicazione: (2025)
• Token-Modification Adversarial Attacks for Natural Language Processing: A Survey
  di: Roth, Tom, et al.
  Pubblicazione: (2021)
• Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections
  di: Maloyan, Narek, et al.
  Pubblicazione: (2025)
• Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
  di: Eiras, Francisco, et al.
  Pubblicazione: (2025)