CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models

Ähnliche Einträge

• CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
  von: Li, Qiming, et al.
  Veröffentlicht: (2026)
• CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
  von: Ye, Zekai, et al.
  Veröffentlicht: (2025)
• Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
  von: Li, Qiming, et al.
  Veröffentlicht: (2025)
• Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
  von: Zhong, Weihong, et al.
  Veröffentlicht: (2024)
• Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
  von: Li, Qiming, et al.
  Veröffentlicht: (2025)