Segment-Level Coherence for Robust Harmful Intent Probing in LLMs

Documenti analoghi

• Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
  di: Sel, Bilgehan, et al.
  Pubblicazione: (2026)
• Mitigating Jailbreaks with Intent-Aware LLMs
  di: Yeo, Wei Jie, et al.
  Pubblicazione: (2025)
• HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
  di: Belkhiter, Yannis, et al.
  Pubblicazione: (2024)
• TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
  di: He, Xuanli, et al.
  Pubblicazione: (2024)
• Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
  di: Tong, Yao, et al.
  Pubblicazione: (2024)