When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs

Documenti analoghi

• Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
  di: Deng, Wenlong, et al.
  Pubblicazione: (2026)
• MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation
  di: Wu, Wenlong, et al.
  Pubblicazione: (2025)
• LLM-Assisted Content Conditional Debiasing for Fair Text Embedding
  di: Deng, Wenlong, et al.
  Pubblicazione: (2024)
• On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
  di: Deng, Wenlong, et al.
  Pubblicazione: (2025)
• Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
  di: Zhang, Qianchi, et al.
  Pubblicazione: (2026)