Lignende værker

• FRAPPE: $\underline{\text{F}}$ast $\underline{\text{Ra}}$nk $\underline{\text{App}}$roximation with $\underline{\text{E}}$xplainable Features for Tensors
  af: Shiao, William, et al.
  Udgivet: (2022)
• CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors
  af: Kadali, Sri Durga Sai Sowmya, et al.
  Udgivet: (2025)
• Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
  af: Li, Jerry, et al.
  Udgivet: (2025)
• Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?
  af: Kadali, Sri Durga Sai Sowmya, et al.
  Udgivet: (2025)
• Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
  af: Kadali, Sri Durga Sai Sowmya, et al.
  Udgivet: (2026)