Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models

Documenti analoghi

• Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
  di: Chen, Kexin, et al.
  Pubblicazione: (2024)
• ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal
  di: Zhang, Haonan, et al.
  Pubblicazione: (2025)
• LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
  di: Zhang, Haonan, et al.
  Pubblicazione: (2026)
• SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications
  di: Lansiaux, Edouard, et al.
  Pubblicazione: (2025)
• Adversarial Attacks on AI-Generated Text Detection Models: A Token Probability-Based Approach Using Embeddings
  di: Kadhim, Ahmed K., et al.
  Pubblicazione: (2025)