HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models

Documenti analoghi

• VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding
  di: Wang, Jiaqi, et al.
  Pubblicazione: (2024)
• AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models
  di: Gao, Yifei, et al.
  Pubblicazione: (2024)
• Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning
  di: Hu, Rui, et al.
  Pubblicazione: (2024)
• ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models
  di: Tu, Yahan, et al.
  Pubblicazione: (2024)
• O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
  di: Cai, Yuchen, et al.
  Pubblicazione: (2024)