Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models

Documenti analoghi

• Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction
  di: Zhang, Yuanhong, et al.
  Pubblicazione: (2026)
• Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
  di: Yin, Jianghao, et al.
  Pubblicazione: (2026)
• Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering
  di: Jana, Soumyadeep, et al.
  Pubblicazione: (2026)
• Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
  di: Chen, Xinrong, et al.
  Pubblicazione: (2026)
• Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
  di: Liu, Shuliang, et al.
  Pubblicazione: (2026)