REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Documenti analoghi

• SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
  di: Liang, Buyun, et al.
  Pubblicazione: (2025)
• KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
  di: Liang, Buyun, et al.
  Pubblicazione: (2025)
• Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation
  di: Kinfu, Kaleab A., et al.
  Pubblicazione: (2025)
• PaCE: Parsimonious Concept Engineering for Large Language Models
  di: Luo, Jinqi, et al.
  Pubblicazione: (2024)
• Conformal Information Pursuit for Interactively Guiding Large Language Models
  di: Chan, Kwan Ho Ryan, et al.
  Pubblicazione: (2025)