HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs

Documenti analoghi

• HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
  di: Dasgupta, Sharanya, et al.
  Pubblicazione: (2025)
• ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models
  di: Dasgupta, Sharanya, et al.
  Pubblicazione: (2026)
• Revealing the Ancient Beauty: Digital Reconstruction of Temple Tiles using Computer Vision
  di: Basu, Arkaprabha
  Pubblicazione: (2025)
• Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
  di: Wang, Chao, et al.
  Pubblicazione: (2025)
• Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
  di: Lu, Yifan, et al.
  Pubblicazione: (2025)